Daily Papers

Multimodal large language models (MLLMs) struggle with hallucinations, particularly with fine-grained queries, a challenge underrepresented by existing benchmarks that focus on coarse image-related questions. We introduce FIne-grained NEgative queRies (FINER), alongside two benchmarks: FINER-CompreCap and FINER-DOCCI. Using FINER, we analyze hallucinations across four settings: multi-object, multi-attribute, multi-relation, and ``what'' questions. Our benchmarks reveal that MLLMs hallucinate when fine-grained mismatches co-occur with genuinely present elements in the image. To address this, we propose FINER-Tuning, leveraging Direct Preference Optimization (DPO) on FINER-inspired data. Finetuning four frontier MLLMs with FINER-Tuning yields up to 24.2\% gains (InternVL3.5-14B) on hallucinations from our benchmarks, while simultaneously improving performance on eight existing hallucination suites, and enhancing general multimodal capabilities across six benchmarks. Code, benchmark, and models are available at https://explainableml.github.io/finer-project/{https://explainableml.github.io/finer-project/}.

While Multimodal Large Language Models (MLLMs) excel at visual understanding, they often struggle in complex scenarios that require visual planning and imagination. Inspired by how humans use sketching as a form of visual thinking to develop and communicate ideas, we introduce Latent Sketchpad, a framework that equips MLLMs with an internal visual scratchpad. The internal visual representations of MLLMs have traditionally been confined to perceptual understanding. We repurpose them to support generative visual thought without compromising reasoning ability. Building on frontier MLLMs, our approach integrates visual generation directly into their native autoregressive reasoning process. It allows the model to interleave textual reasoning with the generation of visual latents. These latents guide the internal thought process and can be translated into sketch images for interpretability. To realize this, we introduce two components: a Context-Aware Vision Head autoregressively produces visual representations, and a pretrained Sketch Decoder renders these into human-interpretable images. We evaluate the framework on our new dataset MazePlanning. Experiments across various MLLMs show that Latent Sketchpad delivers comparable or even superior reasoning performance to their backbone. It further generalizes across distinct frontier MLLMs, including Gemma3 and Qwen2.5-VL. By extending model's textual reasoning to visual thinking, our framework opens new opportunities for richer human-computer interaction and broader applications. More details and resources are available on our project page: https://latent-sketchpad.github.io/.

Multimodal large language models (MLLMs) are now routinely deployed for visual understanding, generation, and curation. A substantial fraction of these applications require an explicit aesthetic judgment. Most existing solutions reduce this judgment to predicting a scalar score for a single image. We first ask whether such scores faithfully capture comparative preference: in a controlled study with eight expert annotators, score-derived rankings align poorly with the same annotators' direct comparisons, while direct ranking yields substantially higher inter-annotator agreement on best- and worst-image labels. Motivated by this finding, we introduce the Visual Aesthetic Benchmark (VAB), which casts aesthetic evaluation as comparative selection over candidate sets with matched subject matter. VAB contains 400 tasks and 1,195 images across fine art, photography, and illustration, with labels derived from the consensus of 10 independent expert judges per task. Evaluating 20 frontier MLLMs and six dedicated visual-quality reward models, we find that the strongest system identifies both the best and the worst image correctly across three random permutations of the candidate order in only 26.5% of tasks, far below the 68.9% achieved by human experts. Fine-tuning a 35B-parameter model on 2,000 expert examples brings its accuracy close to that of a 397B-parameter open-weight model, suggesting that the comparative signal in VAB is transferable. Together, these results expose a clear and measurable gap between current multimodal models and expert aesthetic judgment, and VAB provides the first set-based, expert-grounded testbed on which that gap can be tracked and closed.

Multimodal large language models can write code to produce complex programs as well as use programs to do 3D modeling, which opens up a new avenue for 3D generation powered by their priors, world knowledge and reasoning. Yet existing benchmarks rarely evaluate 3D modeling through code. Such modeling demands more than runnable code: from a text or visual specification, a model must generate a parametric 3D program that is geometrically precise, semantically aligned and assembly-consistent. We introduce P3D-Bench, a benchmark for parametric 3D generation. Unlike a 3D mesh, a parametric 3D program exposes explicit dimensions, construction operations and part relations, revealing whether a model recovers a design's structure, not just its appearance. Under a unified protocol, P3D-Bench covers three task families (Text-to-3D, Image-to-3D and Assembly-3D) and scores each output for executability, geometric fidelity, topology, text-grounded constraints, multiview semantic alignment and part-level structure. We evaluate frontier MLLMs and text-only LLMs on 400 text cases, 400 image cases and 203 annotated assemblies, with domain-specific models as reference points. Our extensive evaluation yields three findings. First, assemblies are the hardest setting, where models still fail to compose multiple parts into a coherent structure. Second, models can often recover the global shape and semantic identity of the target object, yet fail to reproduce the precise parametric geometry specified by the input. Third, part-level modeling remains weak on assemblies, where models recover neither the geometry of each part nor the right number of parts. These results position P3D-Bench as a benchmark for evaluating precise parametric geometry and part-level structure in parametric 3D generation.

Humans develop perception through a bottom-up hierarchy: from basic primitives and Gestalt principles to high-level semantics. In contrast, current Multimodal Large Language Models (MLLMs) are trained directly on complex downstream tasks, often bypassing these foundational visual capabilities. To systematically investigate this gap, we introduce VisFactor, a benchmark that digitizes 20 vision-centric subtests from FRCT, a well-established cognitive psychology assessment spanning four domains of human visual cognition. Furthermore, we design algorithms to automatically construct and validate unlimited test cases with controllable difficulty. Using VisFactor, we evaluate 23 frontier MLLMs, including both proprietary (e.g., GPT, Gemini) and open-source (e.g., LLaMA, Qwen) models. The best model achieves a score of only 30.17%. Models consistently fail on tasks such as mental rotation, spatial relation inference, and figure-ground discrimination, regardless of model size or prompting strategy. These findings suggest that performance improvements on existing general benchmarks might represent castles in the air instead of a genuine mastery of human-like visual cognition.

Human vision is a closed loop: gaze is continuously redirected by intermediate hypotheses rather than a single snapshot. Decades of psychophysics and cognitive science have argued that this active observation is essential for a wide range of tasks. Whether today's multimodal large language models (MLLMs) exercise active observation is an empirical question that current vision-language benchmarks do not answer. We introduce ActiveVision, a benchmark that makes active observation measurable for MLLMs, comprising 17 tasks across 3 categories. Tasks are designed to force repeated visual perception rather than a single static description. Frontier MLLMs collapse on ActiveVision: the highest-scoring model we evaluate, GPT-5.5 at the highest exposed reasoning-effort tier, solves only 10.6% of items and scores zero on 11 of the 17 tasks, and even Claude Fable 5, despite topping most reasoning and coding leaderboards, solves just 3.5%, far behind three human participants who average 96.1%. Furthermore, much of the gap persists even when models write and run their own vision code: such code is unreliable on realistic imagery, and catching its failures itself requires the active perception the models lack. Together, these results indicate that current MLLMs lack robust active visual observation, motivating architectures and training objectives that close the perception-reasoning loop.

Humans perceive far more in a scene than what is explicitly depicted: a single glance captures past causes and future trajectories; a quick peek determines if a vehicle can fit between two parked cars; a few seconds of video reveals who holds authority in a room; and a fleeting clip highlights subtle abstract patterns like unwritten rules or hidden labels. This capacity reflects a form of humanity's sixth sense: an intuitive reasoning mechanism that recovers implicit information beyond raw sensory perception. Crucially, this rapid, zero-shot visual intuition underpins everyday navigation and social interaction, making it a vital capability for Multimodal Large Language Models (MLLMs) deployed alongside people. Existing visual benchmarks, however, target either deliberate expert-level analysis in academic and mathematical domains or low-level perception, leaving the intuitive reasoning that people perform largely untested. To bridge this gap, we introduce Humanity's Sixth Sense (HSS), a benchmark for intuitive visual reasoning. HSS spans diverse image and video inputs, organizes items under a structured taxonomy, and pairs each with human-written prompts probing the implicit temporal, spatial, social, and abstract structure that people infer at a glance. Frontier MLLMs fall short of human performance: participants reach 93.1% accuracy, while the strongest model, GPT-6-astra, reaches only 53.6% even at maximum reasoning effort. Despite excelling in many complex tasks that require advanced perception and knowledge, current models still struggle significantly on these visual tasks that are intuitive for humans. We further explore agentic setup that apply dynamic visual manipulation to HSS, which narrows but does not close the gap. HSS establishes intuitive visual reasoning as a measurable axis and directs attention to a capability that scaling on current benchmarks has so far left behind.

Multimodal large language models (MLLMs) are rapidly evolving toward continuous audio--visual reasoning, creating an urgent need for evaluations that expose their capability limits. Audio--visual captioning is an ideal diagnostic task, yet current benchmarks face a coupled trade-off: whole-caption scores provide coverage without localization, local probes provide localization without coverage, and unconstrained LLM judges introduce instability. We introduce OmniCapBench (Omni-Video Caption Benchmark), a benchmark that reframes audio--visual caption evaluation as a deep-structured diagnostic framework. OmniCapBench shifts the prediction target from free-form text to sets of atomic, verifiable evaluation units across three tracks: entity references, visual shots, and audio events, enabling reliable scoring with deterministic constraint checks and localized LLM-based semantic comparisons. With 786 densely annotated videos, OmniCapBench effectively distinguishes MLLM perception errors, including temporal grounding failures, identity drift, cross-modal misalignment, and hallucinated descriptions. Evaluating frontier MLLMs reveals strong local perception but weak long-horizon audio--visual reasoning, particularly in identity drift and cross-modal misalignment, providing a fine-grained roadmap for omnimodal development.

MLLMs have been widely studied for video question answering recently. However, most existing assessments focus on natural videos, overlooking synthetic videos, such as AI-generated content (AIGC). Meanwhile, some works in video generation rely on MLLMs to evaluate the quality of generated videos, but the capabilities of MLLMs on interpreting AIGC videos remain largely underexplored. To address this, we propose a new benchmark, VF-Eval, which introduces four tasks-coherence validation, error awareness, error type detection, and reasoning evaluation-to comprehensively evaluate the abilities of MLLMs on AIGC videos. We evaluate 13 frontier MLLMs on VF-Eval and find that even the best-performing model, GPT-4.1, struggles to achieve consistently good performance across all tasks. This highlights the challenging nature of our benchmark. Additionally, to investigate the practical applications of VF-Eval in improving video generation, we conduct an experiment, RePrompt, demonstrating that aligning MLLMs more closely with human feedback can benefit video generation.

Multimodal Large Language Models (MLLMs) have achieved significant advances in integrating visual and linguistic information, yet their ability to reason about complex and real-world scenarios remains limited. The existing benchmarks are usually constructed in the task-oriented manner without guarantee that different task samples come from the same data distribution, thus they often fall short in evaluating the synergistic effects of lower-level perceptual capabilities on higher-order reasoning. To lift this limitation, we contribute Lens, a multi-level benchmark with 3.4K contemporary images and 60K+ human-authored questions covering eight tasks and 12 daily scenarios, forming three progressive task tiers, i.e., perception, understanding, and reasoning. One feature is that each image is equipped with rich annotations for all tasks. Thus, this dataset intrinsically supports to evaluate MLLMs to handle image-invariable prompts, from basic perception to compositional reasoning. In addition, our images are manully collected from the social media, in which 53% were published later than Jan. 2025. We evaluate 15+ frontier MLLMs such as Qwen2.5-VL-72B, InternVL3-78B, GPT-4o and two reasoning models QVQ-72B-preview and Kimi-VL. These models are released later than Dec. 2024, and none of them achieve an accuracy greater than 60% in the reasoning tasks. Project page: https://github.com/Lens4MLLMs/lens. ICCV 2025 workshop page: https://lens4mllms.github.io/mars2-workshop-iccv2025/

Multimodal LLMs are increasingly deployed as perceptual backbones for autonomous agents in 3D environments, from robotics to virtual worlds. These applications require agents to perceive rapid state changes, attribute actions to the correct entities, and reason about concurrent multi-agent behaviors from a first-person perspective, capabilities that existing benchmarks do not adequately evaluate. We introduce GameplayQA, a framework for evaluating agentic-centric perception and reasoning through video understanding. Specifically, we densely annotate multiplayer 3D gameplay videos at 1.22 labels/second, with time-synced, concurrent captions of states, actions, and events structured around a triadic system of Self, Other Agents, and the World, a natural decomposition for multi-agent environments. From these annotations, we refined 2.4K diagnostic QA pairs organized into three levels of cognitive complexity, accompanied by a structured distractor taxonomy that enables fine-grained analysis of where models hallucinate. Evaluation of frontier MLLMs reveals a substantial gap from human performance, with common failures in temporal and cross-video grounding, agent-role attribution, and handling the decision density of the game. We hope GameplayQA stimulates future research at the intersection of embodied AI, agentic perception, and world modeling.

Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated impressive performance on standard visual reasoning benchmarks. However, there is growing concern that these models rely excessively on linguistic shortcuts rather than genuine visual grounding, a phenomenon we term Text Bias. In this paper, we investigate the fundamental tension between visual perception and linguistic priors. We decouple the sources of this bias into two dimensions: Internal Corpus Bias, stemming from statistical correlations in pretraining, and External Instruction Bias, arising from the alignment-induced tendency toward sycophancy. To quantify this effect, we introduce V-FAT (Visual Fidelity Against Text-bias), a diagnostic benchmark comprising 4,026 VQA instances across six semantic domains. V-FAT employs a Three-Level Evaluation Framework that systematically increases the conflict between visual evidence and textual information: (L1) internal bias from atypical images, (L2) external bias from misleading instructions, and (L3) synergistic bias where both coincide. We introduce the Visual Robustness Score (VRS), a metric designed to penalize "lucky" linguistic guesses and reward true visual fidelity. Our evaluation of 12 frontier MLLMs reveals that while models excel in existing benchmarks, they experience significant visual collapse under high linguistic dominance.

We introduce PerceptionBench, a benchmark specifically designed to evaluate the atomic visual perception capabilities of Multimodal Large Language Models (MLLMs). Existing benchmarks often fail to isolate perception: holistic evaluations conflate perceptual errors with failures in reasoning or domain knowledge, while application-driven benchmarks only cover narrow, fragmented domains shaped by heuristic designs. To address these limitations, PerceptionBench adopts a bottom-up approach: by diagnosing the earliest failure points in the responses of frontier MLLMs across 42 existing benchmarks, we construct an error taxonomy whose perception branch defines ten atomic perceptual capabilities. Guided by this taxonomy, we construct 3,000 verified questions with short, unambiguous answers, each isolating a single capability, with difficulty stemming from perception rather than reasoning or knowledge. Benchmark results across sixteen frontier MLLMs reveal that atomic perception remains largely unsolved---no model reaches 60\% accuracy, perception-related hallucination is the weakest capability on average, and similar overall scores conceal sharply divergent capability profiles. PerceptionBench thus provides a capability-level standard for measuring and diagnosing the visual perception boundaries of MLLMs.

Multimodal large language models (MLLMs) struggle with spatial, embodied, physical, and temporal reasoning. We hypothesize that these failures reflect a shared deficit in visual transition reasoning, and test whether this capability can serve as a shared training primitive, one that different models can learn from different supervision sources and reuse across different tasks, with a systematic training recipe. Existing benchmarks document these deficits separately but do not support controlled comparisons across scenes, actions, and reasoning operations. We therefore introduce WOVEN, a training source and benchmark for visual transition reasoning that organizes transition supervision by scene, action, and reasoning type, using diverse, realistic rollouts from video-pretrained generative models: 36,076 examples across 20 scene types, 5 action types, and 8 reasoning types. We first evaluate 38 frontier MLLMs (e.g., GPT-5.4 and Qwen3-VL-235B-A22B) and find a substantial and systematic deficit: even the strongest models fall far below humans, and the failures recur across model families and persist with scale. We then train MLLMs at multiple scales on WOVEN and find that they learn a shared capability that transfers broadly: training subsets of only about 2,000 items each collectively improve 22 of 26 external benchmarks by up to 27.3 percentage points, and WOVEN data can replace 30-50% of a task's own training data with comparable accuracy. Controlled comparisons further yield a training recipe for visual world modeling, validated prospectively on held-out benchmarks: select supervision by the reasoning operation it teaches rather than by the actions, scenes, or domains it shows, and prefer larger changes to the visual state for robustness. Our work establishes visual transition reasoning as a reusable foundation for systematic visual world-model training in MLLMs.

People have long dreamed of an assistant that is always there to guide them and remind what they forget, from new dishes to lost keys. Powered by multimodal large language models (MLLMs), egocentric AI assistants on wearable devices are bringing this dream within reach: they see what the user sees and give instructions for user's physical work when necessary. However, testing such assistance is challenging and usually requires real people. The expensive and rare real interaction data leaves a key question unanswered: Can today's MLLMs truly help people in physical world? To answer this question, we propose InteractiveWorld, the first verifiable environment for closed-loop interaction between human and AI assistant. Unlike existing robot-centric simulators, InteractiveWorld lets the assistant guide a human agent who observes the scene, understands instructions, and acts independently. It thus realistically simulates how AI assistant collaborates with human: the assistant instructs, the human acts, and the environment executes actions and updates what they see next. Building on it, we introduce InteractiveBench, the first dynamic benchmark for egocentric AI assistants, with 120 multi-turn tasks across six categories. In each task, the assistant guides the human in real time, and every instruction shapes the outcome, which is scored by verifiable, state-based rewards. Experiments with 12 frontier MLLMs show they are still far from reliable assistants. Even the strongest model, Claude Fable 5.1, achieves at most 20% and 25% on long-horizon Guidance and Planning tasks, respectively. Overall, our work offers a verifiable platform and a rigorous evaluation set, laying a solid foundation for research on interactive MLLM assistants that truly help people in the physical world.

Constructing an interactive 3D open world from a user query is important. However, existing methods are primarily evaluated on idealized, simple queries, making it difficult to systematically analyze and compare how multimodal agents understand user intent, use 3D tools, and reason over textual and visual 3D world information. To this end, we propose VibeWorlding, a unified framework for benchmarking and training vibe worlding agents: a multimodal agent that can autonomously infer user intent, plan scene layout, invoke 3D tools, and reflect on the multimodal feedback in a multi-turn agent-environment interaction process. To achieve this, we first build VWE-BENCH, a benchmark of 2,616 high-quality 3D assets, 323 human-annotated seed 3D worlds, and 6,828 reverse-synthesized multimodal user queries, split into verified queries with ground-truth and unverified queries with carefully designed rubrics. Moreover, we develop VibeWorlding-Gym, a joint multimodal RL post-training framework that integrates (1) a sandbox environment unifying asset retrieval, editing, and image rendering as MCP tools, and (2) a rubric-based verifier that combines physical feasibility and intent fulfillment verification, supporting both fair model evaluation and scalable multimodal RL reward service. Our experiments show that current frontier MLLMs are far from solving the vibe worlding agent task, with even GPT-5.5 and Qwen3.8-Max reaching below 60% success rate, and trace the bottleneck to precise 3D world editing. We further find that RL training can ease this weakness and enable open-source MLLMs to even surpass closed-source frontiers: our VibeWorlder-8B is comparable to frontier MLLMs, while our flagship VibeWorlder-30B-A3B attains the best overall Pass@1 among all evaluated models.

MLLMs have shown strong zero-shot capabilities across diverse inputs such as across images, video, audio, and text. A crucial, yet underexplored, application of these models lies in understanding and modeling animal-centric scenarios. As animals are integral to millions of households, benchmarking next-generation AI models on pet-focused tasks, ranging from recognizing distress signals to enabling responsive robotic companions, is essential for building AI systems that can work alongside us. We introduce K9-Bench, a novel benchmark focused on real-world domestic dog videos, specifically targeting canine action and interaction understanding via approximately 5000 question-answer pairs across 907 videos spanning 5 distinct task categories that test long-form, canine-centric multimodal reasoning in MLLMs. To create this dataset, we propose a scalable, VLM/LLM-powered data generation pipeline that automatically mines canine-centric videos from the web and curates QA pairs requiring fine-grained, multi-hop reasoning over canine actions and temporally extended interaction sequences. We implement bias mitigation strategies designed to eliminate biases introduced by VLMs during dataset curation. Through extensive experimentation, we find that frontier MLLMs exhibit limited zero-shot performance on canine-centric tasks: although state-of-the-art closed-source models outperform open-source counterparts, they still struggle with compositional reasoning over subtle posture and interaction cues spread over long horizons. We observe that generic chain-of-thought prompting provides only modest performance for such long-horizon reasoning. Beyond a novel dataset for canine activity analysis, K9-Bench provides a general-purpose dataset construction pipeline that can be adapted to other low-data domains for quantitative analysis. Our project website is available at: https://ogmenrobotics.github.io/K9Bench.

Large-scale document processing requires contextually aware table extraction (TE) that is both accurate and efficient. Yet current approaches require billions of parameters, hundreds of autoregressive steps, or costly API inference. Motivated by this, we introduce the Page-Object Table Transformer (POTATR), a lightweight 29M parameter image-to-graph model that extends the Table Transformer (TATR) for contextualized page-level TE. POTATR outperforms all models tested on the PubTables-v2 Single Pages benchmark -- including frontier MLLMs -- achieving GriTS_Con of 0.964 while running over 130times faster at roughly 300times lower cost. Further, POTATR's output is spatially grounded: every recognized element has a bounding box, enabling visual verification and geometric text assignment. As a result, POTATR performs unified page-level TE while composing with other models, enabling extension to scanned documents via external OCR and to full-document TE via techniques like cross-page merging. Code and models will be released.

In real-world applications, models are expected to perform reliably across diverse settings. Yet, many existing multimodal benchmarks expand task types without capturing the visual diversity needed to handle open-ended visual inputs. We present WorldBench, a challenging and visually diverse reasoning benchmark to evaluate Multimodal Large Language Models (MLLMs). We build a taxonomy of thousands of visual concepts across multiple domains (e.g., living things). Guided by this taxonomy, we curate a broad collection of images from search engines and existing datasets to comprehensively represent the visual world. Through structured trial-and-error, we manually design challenging questions that frontier MLLMs fail to answer. On quantitative and human evaluations, WorldBench achieves higher visual diversity than any existing diverse benchmark. Evaluating 15 MLLMs on WorldBench reveals weaknesses in visual understanding: even the strongest model reaches only 64.0% accuracy, while some models perform marginally above chance-level. We hope our work highlights the importance of visual diversity in building multimodal benchmarks.

We explore how multimodal Large Language Models (mLLMs) can help researchers transcribe historical documents, extract relevant historical information, and construct datasets from historical sources. Specifically, we investigate the capabilities of mLLMs in performing (1) Optical Character Recognition (OCR), (2) OCR Post-Correction, and (3) Named Entity Recognition (NER) tasks on a set of city directories published in German between 1754 and 1870. First, we benchmark the off-the-shelf transcription accuracy of both mLLMs and conventional OCR models. We find that the best-performing mLLM model significantly outperforms conventional state-of-the-art OCR models and other frontier mLLMs. Second, we are the first to introduce multimodal post-correction of OCR output using mLLMs. We find that this novel approach leads to a drastic improvement in transcription accuracy and consistently produces highly accurate transcriptions (<1% CER), without any image pre-processing or model fine-tuning. Third, we demonstrate that mLLMs can efficiently recognize entities in transcriptions of historical documents and parse them into structured dataset formats. Our findings provide early evidence for the long-term potential of mLLMs to introduce a paradigm shift in the approaches to historical data collection and document transcription.

As audio-visual multi-modal large language models (MLLMs) are increasingly deployed in safety-critical applications, understanding their vulnerabilities is crucial. To this end, we introduce Multi-Modal Typography, a systematic study examining how typographic attacks across multiple modalities adversely influence MLLMs. While prior work focuses narrowly on unimodal attacks, we expose the cross-modal fragility of MLLMs. We analyze the interactions between audio, visual, and text perturbations and reveal that coordinated multi-modal attack creates a significantly more potent threat than single-modality attacks (attack success rate = 83.43% vs 34.93%).Our findings across multiple frontier MLLMs, tasks, and common-sense reasoning and content moderation benchmarks establishes multi-modal typography as a critical and underexplored attack strategy in multi-modal reasoning. Code and data will be publicly available.

Deploying multimodal foundation models as closed-loop policies increasingly requires conditioning actions on observations that are no longer visible. However, existing benchmarks either expose the full state, conflate hidden-state reconstruction with other agent skills, or test recall only after an episode has ended. We introduce RNG-Bench (Reconstructive Non-Markov Games), a benchmark suite designed to isolate a base model's ability to reconstruct past observations and act on them during multi-step interaction. RNG-Bench includes two complementary games: Matching Pairs, where card identities briefly revealed at specific locations must later be recalled, and 3D Maze, where egocentric views must be integrated into a spatial map. Both games are evaluated under a unified harness with three controlled difficulty axes: grid size, visual pattern, and observation modality. The benchmark further introduces a head-to-head duel protocol to control for instance-level variance and a Memory Gap metric that disentangles forgetting from poor action selection. The hardest configurations require contexts of roughly 128K tokens and 350 image inputs per episode, and remain far from saturated by frontier MLLMs. Memory Gap analysis shows that most residual errors stem from forgetting earlier observations rather than from suboptimal decision making. Finally, fine-tuning Qwen3.5-9B on optimal-policy rollouts and filtered model demonstrations improves performance on RNG-Bench and transfers to existing benchmarks without degrading general multimodal capability.

Multimodal large language models have become the dominant paradigm for visual understanding, but incur substantial costs by encoding inputs into dense, fixed-size patch tokens. However, visual information is unevenly distributed: some regions require fine-grained detail, while others admit compact representations. Downsampling sacrifices this detail, while existing token pruning and adaptive approaches remain limited in content-adaptive granularity, task generalization, and integration with modern MLLMs and serving infrastructure. Overcoming these limitations calls for foundation models that learn, end to end, where-and at what granularity-to allocate visual representations, a native capability we term elastic visual representation weaving. We introduce VisionWeave, establishing this capability in frontier-level MLLMs through large-scale training. It combines two components: a gated spatial pooler constructs coarse-grained representations alongside native fine-grained representations within a shared MRoPE coordinate, while a granularity router learns their content-adaptive allocation. Through self-distillation alone, we validate this capability on Qwen3.5-4B and scale to Qwen3.8-27B with over 30K A100 GPU-hours. Based on Qwen3.8-27B, VisionWeave adaptively adjusts token savings to visual content, saving 43.0% tokens on average while retaining 98.9% native performance across eight benchmarks, versus only 88% performance preserved for token pruning baselines with a fixed 50% savings target. Extensive evaluations confirm robust efficiency-quality trade-offs across diverse tasks, resolutions and video frames. When deployed on SGLang serving engine, our method achieves a 2.3x throughput gain while reducing mean TTFT by 54.4% and mean TPOT by 60.6%. Together, we believe these results position elastic visual weaving as a promising capability for next-generation multimodal models.

Multimodal large language models (MLLMs) often know the rule but pick the wrong answer: on abstract visual reasoning (AVR) tasks, a model can describe what it sees and name the underlying pattern, yet still fail to choose the matching candidate. Existing AVR benchmarks cannot detect this because they collapse perception, rule induction, and answer selection into a single right-or-wrong signal. We introduce StemBind, a shared-stem diagnostic benchmark that probes the same visual stem with three aligned questions: Perception (what is in the image), Rule (what pattern governs it), and Full (which option completes it), so a final-answer error can be attributed to a specific sub-step on the same evidence. StemBind contains 2,298 curated knowledge-light stems across nine auditable visual operations, totaling 19,533 P/R/F tasks, with each full item annotated by Sternberg's four reasoning stages (S1 Encode, S2 Infer, S3 Map, S4 Apply). Evaluating 24 frontier MLLM configurations yields four findings. (i) The R-F chasm: rule accuracy exceeds full-item accuracy on 22 of 24 models, so most failures happen after the rule is identified. (ii) A persistent binding gap: even when P and R are both correct on the same stem, models still answer F incorrectly 51.2% of the time. (iii) The bottleneck is S3: process diagnostics and Stage-wise Stimulus Augmentation localize the dominant failure to rule-to-instance mapping. (iv) Scaling and thinking do not help: neither larger models nor explicit thinking mode reliably closes the gap, and thinking even lowers rule and full-item accuracy. StemBind reframes AVR evaluation from final-answer ranking to locating where abstract visual reasoning breaks down, identifying rule-to-instance binding as a concrete next target for vision-grounded reasoning.

Vision-and-Language Navigation (VLN) requires embodied agents to ground language in visual observations and make long-horizon decisions. Existing methods often address these demands through task-specific architectures. As multimodal large language models (MLLMs) become increasingly capable, an important question remains: Have we truly unlocked the potential of native MLLMs for VLN before introducing task-specific architecture? We present SimpleVLN, an architecture-preserving framework developed through studies of navigation formulation, data construction, and optimization. At the formulation level, SimpleVLN combines single-turn decision inputs with fixed-budget global-local memory to efficiently use navigation history without unbounded context growth, while action chunks enable efficient output of multiple primitive actions per model invocation. For data construction, we combine expert demonstrations with policy-dependent DAgger experience and develop a scalable synthesis pipeline that generates large-scale tasks for reinforcement learning. At the optimization level, a progressive IL-DAgger-RL pipeline advances from action imitation to task-level outcome optimization. Comprehensive experiments validate the effectiveness of these three aspects. We instantiate SimpleVLN across multiple MLLM backbones and model sizes, demonstrating its generality. SimpleVLN achieves 76.7% and 80.1% success rates on the R2R-CE and RxR-CE splits, respectively, substantially outperforming existing methods. These results show that the navigation capabilities of native MLLMs can be effectively unlocked without task-specific architectural designs.

Multimodal Large Language Models (MLLMs) are undergoing rapid progress and represent the frontier of AI development. However, their training and inference efficiency have emerged as a core bottleneck in making MLLMs more accessible and scalable. To address the challenges, we present MiniCPM-V 4.5, an 8B parameter model designed for high efficiency and strong performance. We introduce three core improvements in model architecture, data strategy and training method: a unified 3D-Resampler model architecture for highly compact encoding over images and videos, a unified learning paradigm for document knowledge and text recognition without heavy data engineering, and a hybrid reinforcement learning strategy for proficiency in both short and long reasoning modes. Comprehensive experimental results in OpenCompass evaluation show that MiniCPM-V 4.5 surpasses widely used proprietary models such as GPT-4o-latest, and significantly larger open-source models such as Qwen2.5-VL 72B. Notably, the strong performance is achieved with remarkable efficiency. For example, on the widely adopted VideoMME benchmark, MiniCPM-V 4.5 achieves state-of-the-art performance among models under 30B size, using just 46.7\% GPU memory cost and 8.7\% inference time of Qwen2.5-VL 7B.

Reasoning in multimodal large language models (MLLMs) has shown strong promise in medical imaging. However, this reasoning is usually free-form text judged only by its final answer, making it hard to interpret and verify, especially in 3D radiology, where a diagnosis should be traceable to evidence in the scan. Existing chest CT question-answering datasets compound this by reducing expert radiology reports to answer-only pairs, dropping the reasoning that links findings to conclusions and omitting the patient history clinicians rely on. As a result, reasoning-capable 3D chest CT MLLMs remain out of reach, as neither the structured supervision needed to train them nor the protocol needed to verify their reasoning yet exists. We introduce CORTEX (Clinically Organized Reasoning and sTructured EXplanation), a structured reasoning benchmark for 3D chest CT. For each question, CORTEX restores the missing reasoning as a four-stage diagnostic trace mirroring a radiologist's workflow: task understanding, visual observation, diagnostic reasoning, and answer synthesis. We generate these traces using frontier large language models with broad medical and general-domain knowledge, then filter and verify them with a stage-level evaluation protocol combining automated rubric scoring with expert radiologist review. Crucially, both the reasoning structure and evaluation rubrics are designed in close collaboration with clinicians. Built on CT-RATE, a large, publicly available chest CT dataset without reasoning annotations, CORTEX comprises 76,177 validated reasoning traces across open-ended VQA, closed-ended VQA, and report generation, providing both the structured supervision and the stage-level evaluation protocol needed to build and evaluate trustworthy reasoning models for 3D chest CT. Our dataset and evaluation code will be made publicly available upon acceptance.

Post-training via Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) is crucial for enhancing reasoning in Multimodal Large Language Models (MLLMs), yet existing paradigms often reach a performance bottleneck due to the limitations of static data. While current methods leverage self-reflection or self-evolution to push these boundaries, they still suffer from cognitive drift and hallucinated reasoning paths caused by low-quality synthetic data. To address these challenges, we propose Anchor Evolution (AnE), a new paradigm that integrates truth-anchored data curation and model evolution, achieving faithful and steady performance gains at the reasoning frontier. Specifically, we propose Truth Anchor Expansion, which pinpoints the model failing frontier via trajectory rollouts and leverages ground-truth databases to retrieve high-fidelity anchors for faithful data curation. Subsequently, we introduce the Scaffold-Stripping Mechanism to internalize reasoning capabilities. This mechanism first anchors reasoning paths via scaffold-augmented supervision to mitigate the learning complexity and distribution drift of direct SFT on raw data, then leverages RL to strip the scaffold template, thereby effectively transitioning the reasoning paths into intrinsic model capabilities. Experimental results on multimodal reasoning benchmarks show that our method substantially advances the model performance frontier, improving the base model by 10.3\% across eight multimodal benchmarks and achieving state-of-the-art results. The code will be made publicly available.

Dominant accuracy evaluation might reward unwarranted guessing of Large Language Models, and it might not be applicable to novel tasks for model validation without ground-truth (gt) annotation. Based on basic logic principle, we propose a novel framework to evaluate the vision-language logical consistency of MLLMs on both sufficient and necessary cause-effect relations. We define Vision-Language Logical Consistency Metric (VL-LCM) on traditional MC-VQA tests, and recent NaturalBench tests without the need for gt annotation. Through systematic experiments on representative VL benchmark MMMU and recent VL challenges like NaturalBench, we evaluated 11 recent open-source MLLMs from 4 frontier families. Our findings reveal that, despite significant progress of recent MLLMs on accuracy, logical consistency lags behind significantly. Extensive evaluations on the correlations of VL-LCM with metrics on gt, the reliability of LCM, and the relation of VL-LCM with response distribution justify the validity and applicability of VL-LCM even without gt annotation. Our findings suggest that, beyond accuracy, logical consistency could be employed for both accuracy and reliability. VL-LCM can also be employed for MLLM selection, validation, and reliable answer justification in novel tasks without gt annotation.

E-commerce short videos represent a high-revenue segment of the online video industry characterized by a goal-driven format and dense multi-modal signals. Current models often struggle with these videos because existing benchmarks focus primarily on general-purpose tasks and neglect the reasoning of commercial intent. In this work, we first propose a multi-modal information density assessment framework to quantify the complexity of this domain. Our evaluation reveals that e-commerce content exhibits substantially higher density across visual, audio, and textual modalities compared to mainstream datasets, establishing a more challenging frontier for video understanding. To address this gap, we introduce E-commerce Video Ads Benchmark (E-VAds), which is the first benchmark specifically designed for e-commerce short video understanding. We curated 3,961 high-quality videos from Taobao covering a wide range of product categories and used a multi-agent system to generate 19,785 open-ended Q&A pairs. These questions are organized into two primary dimensions, namely Perception and Cognition and Reasoning, which consist of five distinct tasks. Finally, we develop E-VAds-R1, an RL-based reasoning model featuring a multi-grained reward design called MG-GRPO. This strategy provides smooth guidance for early exploration while creating a non-linear incentive for expert-level precision. Experimental results demonstrate that E-VAds-R1 achieves a 109.2% performance gain in commercial intent reasoning with only a few hundred training samples.

Multimodal large language models have achieved strong performance across diverse vision-language tasks, yet their capabilities in UAV scenarios remain insufficiently explored. Recent UAV-oriented benchmarks have begun to evaluate MLLMs in aerial scenarios, but they typically focus on scene understanding, event recognition, or navigation completion, rather than jointly assessing the dual-cognition capability required for UAV agents: reasoning about both the UAV's own state and the external environment in multiview spatio-temporal contexts. To address this gap, we present UAV-DualCog, a benchmark for aerial multiview spatio-temporal reasoning built on this dual-cognition perspective. UAV-DualCog includes both image and video tasks to jointly evaluate self-state and environment-state reasoning, while requiring spatial or temporal grounding beyond discrete answer prediction. We also develop an automated pipeline that constructs data from scene-level semantic point clouds, yielding a scalable benchmark with diverse scenes, hundreds of landmarks, and thousands of QA samples. Extensive evaluations show that current MLLMs remain far from reliable in UAV dual cognition. Self-state reasoning, viewpoint transformation, precise spatial grounding, and temporal interval localization are persistent bottlenecks, and additional validation with thinking/frontier models and a human baseline confirms that the benchmark is understandable to humans but challenging for existing models. We further construct UAV-DualCog-Train from disjoint scenes and show through a lightweight optimization probe that it provides useful structured supervision, suggesting its value not only as an evaluation benchmark but also as a data resource for advancing MLLM-based UAV agents. Project website and supplementary materials: https://uav-dualcog.lozumi.com

A key frontier for Multimodal Large Language Models (MLLMs) is the ability to perform deep mathematical and spatial reasoning directly from images, moving beyond their established success in semantic description. Mathematical surface plots provide a rigorous testbed for this capability, as they isolate the task of reasoning from the semantic noise common in natural images. To measure progress on this frontier, we introduce MaRVL-QA (Mathematical Reasoning over Visual Landscapes), a new benchmark designed to quantitatively evaluate these core reasoning skills. The benchmark comprises two novel tasks: Topological Counting, identifying and enumerating features like local maxima; and Transformation Recognition, recognizing applied geometric transformations. Generated from a curated library of functions with rigorous ambiguity filtering, our evaluation on MaRVL-QA reveals that even state-of-the-art MLLMs struggle significantly, often resorting to superficial heuristics instead of robust spatial reasoning. MaRVL-QA provides a challenging new tool for the research community to measure progress, expose model limitations, and guide the development of MLLMs with more profound reasoning abilities.

Frontier models are transitioning from multimodal large language models (MLLMs) that merely ingest visual information to unified multimodal models (UMMs) capable of native interleaved generation. This shift has sparked interest in using intermediate visualizations as a reasoning aid, akin to human mental imagery. Central to this idea is the ability to form, maintain, and manipulate visual representations in a goal-oriented manner. To evaluate and probe this capability, we develop MentisOculi, a procedural, stratified suite of multi-step reasoning problems amenable to visual solution, tuned to challenge frontier models. Evaluating visual strategies ranging from latent tokens to explicit generated imagery, we find they generally fail to improve performance. Analysis of UMMs specifically exposes a critical limitation: While they possess the textual reasoning capacity to solve a task and can sometimes generate correct visuals, they suffer from compounding generation errors and fail to leverage even ground-truth visualizations. Our findings suggest that despite their inherent appeal, visual thoughts do not yet benefit model reasoning. MentisOculi establishes the necessary foundation to analyze and close this gap across diverse model families.

Video understanding is a fundamental task for evaluating the capabilities of multimodal large language models (MLLMs). However, existing leading models have already achieved approximately 90% accuracy on the Video-MME leaderboard, suggesting that conventional single-turn video understanding tasks are becoming increasingly saturated and insufficient for assessing the intelligence of advanced MLLMs. Towards this end, we introduce VideoGAIA, an agentic video understanding benchmark for general artificial intelligence (AI) assistants. Moving beyond one-shot video question answering, VideoGAIA formulates video understanding as a multi-turn, tool-augmented interaction process, where models must iteratively perceive videos, invoke external tools, gather complementary information, and integrate multimodal evidence across turns. VideoGAIA contains 271 model-human co-designed tasks covering diverse and complex real-world scenarios. Each video-question-answer instance is independently verified by three human experts to ensure both correctness and appropriate difficulty. All evaluated MLLMs, including frontier models such as GPT-5.5 and Kimi-K3, achieve less than 60% accuracy on VideoGAIA, highlighting its value as a high-quality and timely benchmark for evaluating next-generation MLLMs. We hope that VideoGAIA will facilitate the transition from conventional video understanding toward agentic video understanding.

Recent advances in large language models have catalyzed the development of multimodal LLMs (MLLMs) that integrate text, speech, and vision within unified frameworks. As MLLMs evolve from narrow, monolingual, task-specific systems to general-purpose instruction-following models, a key frontier lies in evaluating their multilingual and multimodal capabilities over both long and short contexts. However, existing benchmarks fall short in evaluating these dimensions jointly: they are often limited to English, mostly focus on one single modality at a time, rely on short-form contexts, or lack human annotations -- hindering comprehensive assessment of model performance across languages, modalities, and task complexity. To address these gaps, we introduce MCIF (Multimodal Crosslingual Instruction Following), the first multilingual human-annotated benchmark based on scientific talks that is designed to evaluate instruction-following in crosslingual, multimodal settings over both short- and long-form inputs. MCIF spans three core modalities -- speech, vision, and text -- and four diverse languages (English, German, Italian, and Chinese), enabling a comprehensive evaluation of MLLMs' abilities to interpret instructions across languages and combine them with multimodal contextual information. MCIF is released under a CC-BY 4.0 license to encourage open research and progress in MLLMs development.

Spatial intelligence is a critical frontier for Multimodal Large Language Models (MLLMs), empowering them to comprehend the physical world. Drawing inspiration from human perception mechanisms, existing studies attempt to construct a coherent spatial understanding via grid-based cognitive maps from multi-frame visual inputs. However, current grid-based map methods rely on discretized raster representations, which limit the model's ability in fine-grained spatial reasoning. To overcome this limitation, we propose Video2Layout, a framework for reconstructing metric-grounded spatial layouts from video. The framework employs continuous object boundary coordinates to quantify inter-object physical distances and object size. This empowers the model with quantitative spatial computation capabilities, effectively alleviating the inherent ambiguity when describing spatial relationships in natural language. Specifically, our method comprises two core stages. First, in supervised fine-tuning stage, we construct a high-quality dataset from the AI2THOR simulator, which enables the model to learn the mapping from visual inputs to precise boundary coordinates. Subsequently, a reinforcement fine-tuning stage further enhances the model's real-world generalization capabilities. To systematically evaluate the correlation between cognitive map accuracy and image quantity, as well as how the quantity of image inputs affects spatial reasoning accuracy, we introduce QVS-Bench, a diagnostic benchmark designed to analyze the relevant mechanisms. Evaluated on QVS-Bench and mainstream spatial reasoning benchmarks, our model, V2LO-7B achieves an average improvement of 4.92% over the model trained on grid maps, validating the superiority of our method. Our code is available at https://github.com/ybrrraway/Video2Layout.

Leveraging Multi-modal Large Language Models (MLLMs) to accelerate frontier scientific research is promising, yet how to rigorously evaluate such systems remains unclear. Existing benchmarks mainly focus on single-document understanding, whereas real scientific workflows require integrating evidence from multiple papers, including their text, tables, and figures. As a result, multi-modal, multi-document scientific reasoning remains underexplored and lacks systematic evaluation. To address this gap, we introduce PaperScope, a multi-modal multi-document benchmark designed for agentic deep research. PaperScope presents three advantages: (1) Structured scientific grounding. It is built on a knowledge graph of over 2,000 AI papers spanning three years, providing a structured foundation for research-oriented queries. (2) Semantically dense evidence construction. It integrates semantically related key information nodes and employs optimized random-walk article selector to sample thematically coherent paper sets, thereby ensuring adequate semantic density and task complexity. (3) Multi-task evaluation of scientific reasoning. It contains over 2,000 QA pairs across reasoning, retrieval, summarization, and problem solving, enabling evaluation of multi-step scientific reasoning. Experimental results show that even advanced systems such as OpenAI Deep Research and Tongyi Deep Research achieve limited scores on PaperScope, highlighting the difficulty of long-context retrieval and deep multi-source reasoning. PaperScope thus provides a rigorous benchmark alongside a scalable pipeline for constructing large-scale multi-modal, multi-source deep research datasets.

We introduce CRYSTAL (Clear Reasoning via Yielded Steps, Traceability, and Logic), a diagnostic benchmark with 6,372 instances that evaluates multimodal reasoning through verifiable intermediate steps. We propose two complementary metrics: Match F1, which scores step-level precision and recall via semantic similarity matching, and Ordered Match F1, which further penalizes disordered reasoning chains. References are constructed through a Delphi-inspired pipeline in which four independent MLLMs generate trajectories, which are then aggregated via semantic clustering and validated through human quality gates. Evaluation of 20 MLLMs, including commercial frontier systems not used during benchmark construction, reveals systematic failures that are invisible to answer accuracy: universal cherry-picking (precision far exceeds recall), non-monotonic scaling trade-offs, and disordered reasoning in which no competitive model preserves more than 60% of matched steps in the correct order. Beyond evaluation, we propose the Causal Process Reward (CPR), a multiplicative reward that couples answer correctness with step-level alignment, and CPR-Curriculum, which progressively increases reasoning difficulty during training. CPR-Curriculum achieves a 32% improvement in Match F1 via GRPO where additive reward strategies fail, improving reasoning without manual step annotation.

As current Multimodal Large Language Models rapidly saturate canonical visual reasoning benchmarks, a key question emerges: do these strong scores genuinely reflect robust visual understanding? We identify a pervasive vulnerability, the Cartesian Shortcut: visual reasoning benchmarks prevalently build on orthogonal grid-based layouts that can be readily discretized into explicit textual coordinates. Models systematically exploit this property, heavily leveraging text-based deductive reasoning to assist visual problem-solving. To systematically dismantle this shortcut, we introduce Polaris-Bench, which re-formulates 53 visual reasoning tasks in Polar coordinate space with paired Cartesian counterparts as reference, while preserving consistent logical constraints and task semantics -- thus fundamentally breaking the orthogonal prior that models exploit. Comprehensive evaluation across 14 state-of-the-art MLLMs reveals that frontier models achieving 70--83% on Cartesian layouts collapse to 31--39% on Polar equivalents, with degradation persisting even under complete logical equivalence. Moreover, reasoning gains observed on Cartesian layouts are severely diminished on Polar equivalents. These findings expose a critical deficiency in current MLLMs: the lack of topology-invariant visual reasoning.

Recent advances in Multimodal Large Language Models (MLLMs) have significantly pushed the frontier of egocentric video question answering (EgocentricQA). However, existing benchmarks and studies are mainly limited to common daily activities such as cooking and cleaning. In contrast, real-world deployment inevitably encounters domain shifts, where target domains differ substantially in both visual style and semantic content. To bridge this gap, we introduce EgoCross, a comprehensive benchmark designed to evaluate the cross-domain generalization of MLLMs in EgocentricQA. EgoCross covers four diverse and challenging domains, including surgery, industry, extreme sports, and animal perspective, representing realistic and high-impact application scenarios. It comprises approximately 1,000 QA pairs across 798 video clips, spanning four key QA tasks: prediction, recognition, localization, and counting. Each QA pair provides both OpenQA and CloseQA formats to support fine-grained evaluation. Extensive experiments show that most existing MLLMs, whether general-purpose or egocentric-specialized, struggle to generalize to domains beyond daily life, highlighting the limitations of current models. Furthermore, we conduct several pilot studies, \eg, fine-tuning and reinforcement learning, to explore potential improvements. We hope EgoCross and our accompanying analysis will serve as a foundation for advancing domain-adaptive, robust egocentric video understanding. Data and codes will be released at: https://github.com/MyUniverse0726/EgoCross{https://github.com/MyUniverse0726/EgoCross.}

Interleaved text-and-image generation represents a significant frontier for Multimodal Large Language Models (MLLMs), offering a more intuitive way to convey complex information. Current paradigms rely on either image generation or retrieval augmentation, yet they typically treat the two as mutually exclusive paths, failing to unify factuality with creativity. We argue that the next milestone in this field is Agentic Tool Planning, where the model serves as a central controller that autonomously determines when, where, and which tools to invoke to produce interleaved responses for visual-critical queries. To systematically evaluate this paradigm, we introduce ATP-Bench, a novel benchmark comprising 7,702 QA pairs (including 1,592 VQA pairs) across eight categories and 25 visual-critical intents, featuring human-verified queries and ground truths. Furthermore, to evaluate agentic planning independent of end-to-end execution and changing tool backends, we propose a Multi-Agent MLLM-as-a-Judge (MAM) system. MAM evaluates tool-call precision, identifies missed opportunities for tool use, and assesses overall response quality without requiring ground-truth references. Our extensive experiments on 10 state-of-the-art MLLMs reveal that models struggle with coherent interleaved planning and exhibit significant variations in tool-use behavior, highlighting substantial room for improvement and providing actionable guidance for advancing interleaved generation. Dataset and code are available at https://github.com/Qwen-Applications/ATP-Bench.

Charts are a primary medium for conveying quantitative and relational information, yet systematically evaluating chart parsing models remains difficult. Existing benchmarks focus on narrow chart types and leave diagrammatic structures such as flowcharts and mind maps largely unaddressed, while models produce outputs in incompatible formats, and datasets rarely include the printed or hand-drawn images encountered in practice. To address these issues, we introduce ChartArena, a comprehensive bilingual benchmark covering eight chart families spanning both numeric charts and diagrammatic structures, each evaluated across three visual scenarios: digital renderings, printed photos, and hand-drawn photos. The dataset is built via a human-agent collaborative annotation pipeline with multi-stage human verification to ensure annotation reliability. To enable fair cross-model comparison, we further design a format-agnostic evaluation protocol that maps heterogeneous outputs into two canonical semantic spaces, a normalized triple view and a directed graph view, and scores them with structure-aware metrics. Through extensive evaluation of 26 leading MLLMs, we observe three consistent findings: (i) frontier proprietary models such as Gemini 3.1 Pro lead overall, yet the strongest open-source systems are rapidly closing the gap; (ii) document parsing models handle numeric charts reasonably but fall sharply behind on diagrammatic structures; and (iii) expert chart parsers remain limited to narrow chart families. Across all models, radar charts and hand-drawn scenarios stay especially challenging. These findings show that ChartArena exposes clear capability gaps and provides a unified foundation for future progress. ChartArena is publicly available at https://github.com/pspdada/ChartArena.

Multimodal large language models (MLLMs) have shown remarkable capabilities across a broad range of tasks but their knowledge and abilities in the geographic and geospatial domains are yet to be explored, despite potential wide-ranging benefits to navigation, environmental research, urban development, and disaster response. We conduct a series of experiments exploring various vision capabilities of MLLMs within these domains, particularly focusing on the frontier model GPT-4V, and benchmark its performance against open-source counterparts. Our methodology involves challenging these models with a small-scale geographic benchmark consisting of a suite of visual tasks, testing their abilities across a spectrum of complexity. The analysis uncovers not only where such models excel, including instances where they outperform humans, but also where they falter, providing a balanced view of their capabilities in the geographic domain. To enable the comparison and evaluation of future models, our benchmark will be publicly released.

Advertising banners are critical for capturing user attention and enhancing advertising campaign effectiveness. Creating aesthetically pleasing banner designs while conveying the campaign messages is challenging due to the large search space involving multiple design elements. Additionally, advertisers need multiple sizes for different displays and various versions to target different sectors of audiences. Since design is intrinsically an iterative and subjective process, flexible editability is also in high demand for practical usage. While current models have served as assistants to human designers in various design tasks, they typically handle only segments of the creative design process or produce pixel-based outputs that limit editability. This paper introduces a training-free framework for fully automated banner ad design creation, enabling frontier multimodal large language models (MLLMs) to streamline the production of effective banners with minimal manual effort across diverse marketing contexts. We present BannerAgency, an MLLM agent system that collaborates with advertisers to understand their brand identity and banner objectives, generates matching background images, creates blueprints for foreground design elements, and renders the final creatives as editable components in Figma or SVG formats rather than static pixels. To facilitate evaluation and future research, we introduce BannerRequest400, a benchmark featuring 100 unique logos paired with 400 diverse banner requests. Through quantitative and qualitative evaluations, we demonstrate the framework's effectiveness, emphasizing the quality of the generated banner designs, their adaptability to various banner requests, and their strong editability enabled by this component-based approach.

Humans build shared spatial understanding by communicating partial, viewpoint-dependent observations. We ask whether Multimodal Large Language Models (MLLMs) can do the same, aligning distinct egocentric views through dialogue to form a coherent, allocentric mental model of a shared environment. To study this systematically, we introduce COSMIC, a benchmark for Collaborative Spatial Communication. In this setting, two static MLLM agents observe a 3D indoor environment from different viewpoints and exchange natural-language messages to solve spatial queries. COSMIC contains 899 diverse scenes and 1250 question-answer pairs spanning five tasks. We find a consistent capability hierarchy, MLLMs are most reliable at identifying shared anchor objects across views, perform worse on relational reasoning, and largely fail at building globally consistent maps, performing near chance, even for the frontier models. Moreover, we find thinking capability yields consistent gains in anchor grounding, but is insufficient for higher-level spatial communication. To contextualize model behavior, we additionally collect 250 human-human dialogues. Humans achieve 95% aggregate accuracy, leaving significant room for improvement for even the best performing model Gemini-3-Pro-Thinking which achieves 72% aggregate accuracy. Moreover, human conversations become increasingly specific as partners converge on a shared mental model, whereas model dialogues continue to explore new possibilities rather than converging, consistent with a limited ability to build and maintain a robust shared mental model. Our code and data is available at https://github.com/ankursikarwar/Cosmic

Electronic Navigational Charts (ENCs) are the safety-critical backbone of modern maritime navigation, yet it remains unclear whether multimodal large language models (MLLMs) can reliably interpret them. Unlike natural images or conventional charts, ENCs encode regulations, bathymetry, and route constraints via standardized vector symbols, scale-dependent rendering, and precise geometric structure -- requiring specialized maritime expertise for interpretation. We introduce ENC-Bench, the first benchmark dedicated to professional ENC understanding. ENC-Bench contains 20,490 expert-validated samples from 840 authentic National Oceanic and Atmospheric Administration (NOAA) ENCs, organized into a three-level hierarchy: Perception (symbol and feature recognition), Spatial Reasoning (coordinate localization, bearing, distance), and Maritime Decision-Making (route legality, safety assessment, emergency planning under multiple constraints). All samples are generated from raw S-57 data through a calibrated vector-to-image pipeline with automated consistency checks and expert review. We evaluate 10 state-of-the-art MLLMs such as GPT-4o, Gemini 2.5, Qwen3-VL, InternVL-3, and GLM-4.5V, under a unified zero-shot protocol. The best model achieves only 47.88% accuracy, with systematic challenges in symbolic grounding, spatial computation, multi-constraint reasoning, and robustness to lighting and scale variations. By establishing the first rigorous ENC benchmark, we open a new research frontier at the intersection of specialized symbolic reasoning and safety-critical AI, providing essential infrastructure for advancing MLLMs toward professional maritime applications.

Multi-modal large language models (MLLMs) have achieved remarkable success in image- and region-level remote sensing (RS) image understanding tasks, such as image captioning, visual question answering, and visual grounding. However, existing RS MLLMs lack the pixel-level dialogue capability, which involves responding to user instructions with segmentation masks for specific instances. In this paper, we propose GeoPix, a RS MLLM that extends image understanding capabilities to the pixel level. This is achieved by equipping the MLLM with a mask predictor, which transforms visual features from the vision encoder into masks conditioned on the LLM's segmentation token embeddings. To facilitate the segmentation of multi-scale objects in RS imagery, a class-wise learnable memory module is integrated into the mask predictor to capture and store class-wise geo-context at the instance level across the entire dataset. In addition, to address the absence of large-scale datasets for training pixel-level RS MLLMs, we construct the GeoPixInstruct dataset, comprising 65,463 images and 140,412 instances, with each instance annotated with text descriptions, bounding boxes, and masks. Furthermore, we develop a two-stage training strategy to balance the distinct requirements of text generation and masks prediction in multi-modal multi-task optimization. Extensive experiments verify the effectiveness and superiority of GeoPix in pixel-level segmentation tasks, while also maintaining competitive performance in image- and region-level benchmarks.

The rapid development of large language models (LLMs) has been witnessed in recent years. Based on the powerful LLMs, multi-modal LLMs (MLLMs) extend the modality from text to a broader spectrum of domains, attracting widespread attention due to the broader range of application scenarios. As LLMs and MLLMs rely on vast amounts of model parameters and data to achieve emergent capabilities, the importance of data is receiving increasingly widespread attention and recognition. Tracing and analyzing recent data-oriented works for MLLMs, we find that the development of models and data is not two separate paths but rather interconnected. On the one hand, vaster and higher-quality data contribute to better performance of MLLMs, on the other hand, MLLMs can facilitate the development of data. The co-development of multi-modal data and MLLMs requires a clear view of 1) at which development stage of MLLMs can specific data-centric approaches be employed to enhance which capabilities, and 2) by utilizing which capabilities and acting as which roles can models contribute to multi-modal data. To promote the data-model co-development for MLLM community, we systematically review existing works related to MLLMs from the data-model co-development perspective. A regularly maintained project associated with this survey is accessible at https://github.com/modelscope/data-juicer/blob/main/docs/awesome_llm_data.md.

Large language models (LLMs) have demonstrated remarkable capabilities across diverse tasks, but their ability to forecast future events remains understudied. A year ago, large language models struggle to come close to the accuracy of a human crowd. I evaluate state-of-the-art LLMs on 464 forecasting questions from Metaculus, comparing their performance against human superforecasters. Frontier models achieve Brier scores that ostensibly surpass the human crowd but still significantly underperform a group of superforecasters.

As Large Language Models (LLMs) are increasingly deployed as autonomous agents in complex and long horizon settings, it is critical to evaluate their ability to sabotage users by pursuing hidden objectives. We study the ability of frontier LLMs to evade monitoring and achieve harmful hidden goals while completing a wide array of realistic tasks. We evaluate a broad range of frontier LLMs using SHADE (Subtle Harmful Agent Detection & Evaluation)-Arena, the first highly diverse agent evaluation dataset for sabotage and monitoring capabilities of LLM agents. SHADE-Arena consists of complex pairs of benign main tasks and harmful side objectives in complicated environments. Agents are evaluated on their ability to complete the side task without appearing suspicious to an LLM monitor. When measuring agent ability to (a) complete the main task, (b) complete the side task, and (c) avoid detection, we find that the best performing frontier models score 27% (Claude 3.7 Sonnet) and 15% (Gemini 2.5 Pro) as sabotage agents when overseen by Claude 3.6 Sonnet. For current frontier models, success on the side task relies heavily on having access to a hidden scratchpad that is not visible to the monitor. We also use SHADE-Arena to measure models' monitoring abilities, with the top monitor (Gemini 2.5 Pro) achieving an AUC of 0.87 at distinguishing benign and malign transcripts. We find that for now, models still struggle at sabotage due to failures in long-context main task execution. However, our measurements already demonstrate the difficulty of monitoring for subtle sabotage attempts, which we expect to only increase in the face of more complex and longer-horizon tasks.

Multimodal Large Language Models (MLLMs) have achieved remarkable success in vision-language tasks but their remote sensing (RS) counterpart are relatively under explored. Unlike natural images, RS imagery presents unique challenges that current MLLMs struggle to handle, particularly in visual grounding and spatial reasoning. This study investigates the limitations of CLIP-based MLLMs in RS, highlighting their failure to differentiate visually distinct yet semantically similar RS images. To address this, we introduce a remote sensing multimodal visual patterns (RSMMVP) benchmark. It is designed to evaluate MLLMs in RS tasks by identifying the CLIP-blind pairs, where CLIP-based models incorrectly assign high similarity scores to visually distinct RS images. Through a visual question answering (VQA) evaluation, we analyze the performance of state-of-the-art MLLMs, revealing significant limitations in RS specific representation learning. The results provide valuable insights into the weaknesses of CLIP-based visual encoding and offer a foundation for future research to develop more effective MLLMs tailored for remote sensing applications.

Online GUI navigation on mobile devices has driven a lot of attention recent years since it contributes to many real-world applications. With the rapid development of large language models (LLM), multimodal large language models (MLLM) have tremendous potential on this task. However, existing MLLMs need high quality data to improve its abilities of making the correct navigation decisions according to the human user inputs. In this paper, we developed a novel and highly valuable dataset, named E-ANT, as the first Chinese GUI navigation dataset that contains real human behaviour and high quality screenshots with annotations, containing nearly 40,000 real human traces over 5000+ different tinyAPPs. Furthermore, we evaluate various powerful MLLMs on E-ANT and show their experiments results with sufficient ablations. We believe that our proposed dataset will be beneficial for both the evaluation and development of GUI navigation and LLM/MLLM decision-making capabilities.

Multimodal large language models (MLLMs) hold significant potential in medical applications, including disease diagnosis and clinical decision-making. However, these tasks require highly accurate, context-sensitive, and professionally aligned responses, making reliable reward models and judges critical. Despite their importance, medical reward models (MRMs) and judges remain underexplored, with no dedicated benchmarks addressing clinical requirements. Existing benchmarks focus on general MLLM capabilities or evaluate models as solvers, neglecting essential evaluation dimensions like diagnostic accuracy and clinical relevance. To address this, we introduce Med-RewardBench, the first benchmark specifically designed to evaluate MRMs and judges in medical scenarios. Med-RewardBench features a multimodal dataset spanning 13 organ systems and 8 clinical departments, with 1,026 expert-annotated cases. A rigorous three-step process ensures high-quality evaluation data across six clinically critical dimensions. We evaluate 32 state-of-the-art MLLMs, including open-source, proprietary, and medical-specific models, revealing substantial challenges in aligning outputs with expert judgment. Additionally, we develop baseline models that demonstrate substantial performance improvements through fine-tuning.

Multimodal large language models (MLLMs) have demonstrated impressive performance in vision-language tasks across a broad spectrum of domains. However, the large model scale and associated high computational costs pose significant challenges for training and deploying MLLMs on consumer-grade GPUs or edge devices, thereby hindering their widespread application. In this work, we introduce Mini-InternVL, a series of MLLMs with parameters ranging from 1B to 4B, which achieves 90% of the performance with only 5% of the parameters. This significant improvement in efficiency and effectiveness makes our models more accessible and applicable in various real-world scenarios. To further promote the adoption of our models, we develop a unified adaptation framework for Mini-InternVL, which enables our models to transfer and outperform specialized models in downstream tasks, including autonomous driving, medical images, and remote sensing. We believe that our study can provide valuable insights and resources to advance the development of efficient and effective MLLMs. Code is available at https://github.com/OpenGVLab/InternVL.

In the past year, Multimodal Large Language Models (MLLMs) have demonstrated remarkable performance in tasks such as visual question answering, visual understanding and reasoning. However, the extensive model size and high training and inference costs have hindered the widespread application of MLLMs in academia and industry. Thus, studying efficient and lightweight MLLMs has enormous potential, especially in edge computing scenarios. In this survey, we provide a comprehensive and systematic review of the current state of efficient MLLMs. Specifically, we summarize the timeline of representative efficient MLLMs, research state of efficient structures and strategies, and the applications. Finally, we discuss the limitations of current efficient MLLM research and promising future directions. Please refer to our GitHub repository for more details: https://github.com/lijiannuist/Efficient-Multimodal-LLMs-Survey.

Ultra-high-resolution (UHR) remote-sensing (RS) imagery provides fine-grained Earth-observation evidence over city-scale scenes, but poses a fundamental challenge for multimodal large language models (MLLMs): task-relevant evidence is often sparse, local, and spatially dispersed across extremely large visual contexts. A natural solution is to equip MLLMs with zoom-in tools for active local inspection. However, through a pilot study on XLRS-Bench, we find that zoom-in is only partially effective: it resolves easy and medium-level tasks with locally recoverable evidence, but saturates on hard cases requiring global search, multi-region comparison, path planning, or dispersed-evidence reasoning. Motivated by this finding, we move beyond single-tool zoom-in and introduce GeoMTVR, a large-scale Geospatial Multi-Tool Visual Reasoning dataset built from wide-area satellite imagery. GeoMTVR contains 13K UHR VQA samples with interleaved reasoning trajectories, diverse visual tool calls, and returned visual observations, enabling models to learn question decomposition, tool selection, regional inspection, object-level grounding, auxiliary visual reasoning, and cross-tool evidence integration. Beyond supervised fine-tuning, we propose a tool-attention-focused reinforcement learning algorithm that concentrates optimization on critical tool-use decisions, including when to invoke tools, which tool to select, where to apply it, and how to interpret tool outputs. By combining SFT on GeoMTVR with our RL algorithm, we develop GeoLens, a multi-tool visual reasoning MLLM for UHR RS. Experiments show that GeoLens consistently outperforms direct reasoning and single-tool zoom-in baselines, achieving stronger accuracy, better evidence grounding, and more efficient tool-use trajectories.

Multilingual large language models (MLLMs) have shown impressive capabilities across a variety of languages. However, efficacy can differ greatly between different language families, especially for those with limited linguistic resources. This report presents MERaLiON-TextLLM, a series of open-source language models specifically tailored to improve understanding and generation in Chinese, Indonesian, Malay, and Singlish. The initial released model is built on Llama-3-8B-Base and refined through a meticulously crafted process of continued pre-training and weight merging. Our approach achieves performance improvements across benchmarks in these languages, exceeding the capabilities of the official Llama-3 models. We provide the model checkpoints as a resource to support further research and development in cross-lingual language understanding.

Multimodal large language models (MLLMs) represent an evolutionary expansion in the capabilities of traditional large language models, enabling them to tackle challenges that surpass the scope of purely text-based applications. It leverages the knowledge previously encoded within these language models, thereby enhancing their applicability and functionality in the reign of multimodal contexts. Recent works investigate the adaptation of MLLMs to predict free-form answers as a generative task to solve medical visual question answering (Med-VQA) tasks. In this paper, we propose a parameter efficient framework for fine-tuning MLLM specifically tailored to Med-VQA applications, and empirically validate it on a public benchmark dataset. To accurately measure the performance, we employ human evaluation and the results reveal that our model achieves an overall accuracy of 81.9%, and outperforms the GPT-4v model by a significant margin of 26% absolute accuracy on closed-ended questions. The code will be available here: https://github.com/jinlHe/PeFoMed.

The astonishing breakthrough of multimodal large language models (MLLMs) has necessitated new benchmarks to quantitatively assess their capabilities, reveal their limitations, and indicate future research directions. However, this is challenging in the context of remote sensing (RS), since the imagery features ultra-high resolution that incorporates extremely complex semantic relationships. Existing benchmarks usually adopt notably smaller image sizes than real-world RS scenarios, suffer from limited annotation quality, and consider insufficient dimensions of evaluation. To address these issues, we present XLRS-Bench: a comprehensive benchmark for evaluating the perception and reasoning capabilities of MLLMs in ultra-high-resolution RS scenarios. XLRS-Bench boasts the largest average image size (8500times8500) observed thus far, with all evaluation samples meticulously annotated manually, assisted by a novel semi-automatic captioner on ultra-high-resolution RS images. On top of the XLRS-Bench, 16 sub-tasks are defined to evaluate MLLMs' 10 kinds of perceptual capabilities and 6 kinds of reasoning capabilities, with a primary emphasis on advanced cognitive processes that facilitate real-world decision-making and the capture of spatiotemporal changes. The results of both general and RS-focused MLLMs on XLRS-Bench indicate that further efforts are needed for real-world RS applications. We have open-sourced XLRS-Bench to support further research in developing more powerful MLLMs for remote sensing.

Multilingual Large Language Models are capable of using powerful Large Language Models to handle and respond to queries in multiple languages, which achieves remarkable success in multilingual natural language processing tasks. Despite these breakthroughs, there still remains a lack of a comprehensive survey to summarize existing approaches and recent developments in this field. To this end, in this paper, we present a thorough review and provide a unified perspective to summarize the recent progress as well as emerging trends in multilingual large language models (MLLMs) literature. The contributions of this paper can be summarized: (1) First survey: to our knowledge, we take the first step and present a thorough review in MLLMs research field according to multi-lingual alignment; (2) New taxonomy: we offer a new and unified perspective to summarize the current progress of MLLMs; (3) New frontiers: we highlight several emerging frontiers and discuss the corresponding challenges; (4) Abundant resources: we collect abundant open-source resources, including relevant papers, data corpora, and leaderboards. We hope our work can provide the community with quick access and spur breakthrough research in MLLMs.

Steering methods have emerged as effective and targeted tools for guiding large language models' (LLMs) behavior without modifying their parameters. Multimodal large language models (MLLMs), however, do not currently enjoy the same suite of techniques, due in part to their recency and architectural diversity. Inspired by this gap, we investigate whether MLLMs can be steered using vectors derived from their text-only LLM backbone, via sparse autoencoders (SAEs), mean shift, and linear probing. We find that text-derived steering consistently enhances multimodal accuracy across diverse MLLM architectures and visual tasks. In particular, mean shift boosts spatial relationship accuracy on CV-Bench by up to +7.3% and counting accuracy by up to +3.3%, outperforming prompting and exhibiting strong generalization to out-of-distribution datasets. These results highlight textual steering vectors as a powerful, efficient mechanism for enhancing grounding in MLLMs with minimal additional data collection and computational overhead.

The rapid advancement of Multimodal Large Language Models (MLLMs) has empowered Unmanned Aerial Vehicle (UAV) with exceptional capabilities in spatial reasoning, semantic understanding, and complex decision-making, making them inherently suited for UAV Search and Rescue (SAR). However, existing UAV SAR research is dominated by traditional vision and path-planning methods and lacks a comprehensive and unified benchmark for embodied agents. To bridge this gap, we first propose the novel task of Embodied Search and Rescue (ESAR), which requires aerial agents to autonomously explore complex environments, identify rescue clues, and reason about victim locations to execute informed decision-making. Additionally, we present ESARBench, the first comprehensive benchmark designed to evaluate MLLM-driven UAV agents in highly realistic SAR scenarios. Leveraging Unreal Engine 5 and AirSim, we construct four high-fidelity, large-scale open environments mapped directly from real-world Geographic Information System (GIS) data to ensure photorealistic landscapes. To rigorously simulate actual rescue operations, our benchmark incorporates dynamic variables including weather conditions, time of day, and stochastic clue placement. Furthermore, we create a dataset of 600 tasks modeled after real-world rescue cases and propose a robust set of evaluation metrics. We evaluate diverse baselines, ranging from traditional heuristics to advanced ground and aerial MLLM-based ObjectNav agents. Experimental results highlight the challenges in ESAR, revealing critical bottlenecks in spatial memory, aerial adaptation, and the trade-off between search efficiency and flight safety. We hope ESARBench serves as a valuable resource to advance research on Embodied Search and Rescue domain. Source code and project page: https://4amgodvzx.github.io/ESAR.github.io.

Remote sensing imagery presents vast, inherently unstructured spatial data, necessitating sophisticated reasoning to interpret complex user intents and contextual relationships beyond simple recognition tasks. In this paper, we aim to construct an Earth observation workflow to handle complex queries by reasoning about spatial context and user intent. As a reasoning workflow, it should autonomously explore and construct its own inference paths, rather than being confined to predefined ground-truth sequences. Ideally, its architecture ought to be unified yet generalized, possessing capabilities to perform diverse reasoning tasks through one model without requiring additional fine-tuning. Existing remote sensing approaches rely on supervised fine-tuning paradigms and task-specific heads, limiting both autonomous reasoning and unified generalization. To this end, we propose RemoteReasoner, a unified workflow for geospatial reasoning. The design of RemoteReasoner integrates a multi-modal large language model (MLLM) for interpreting user instructions and localizing targets, together with task transformation strategies that enable multi-granularity tasks, including object-, region-, and pixel-level. In contrast to existing methods, our framework is trained with reinforcement learning (RL) to endow the MLLM sufficient reasoning autonomy. At the inference stage, our transformation strategies enable diverse task output formats without requiring task-specific decoders or further fine-tuning. Experiments demonstrated that RemoteReasoner achieves state-of-the-art (SOTA) performance across multi-granularity reasoning tasks. Furthermore, it retains the MLLM's inherent generalization capability, demonstrating robust performance on unseen tasks and out-of-distribution categories.

Multimodal large language models (MLLMs) struggle with numerical regression under long-tailed target distributions. Token-level supervised fine-tuning (SFT) and point-wise regression rewards bias learning toward high-density regions, leading to regression-to-the-mean behavior and poor tail performance. We identify the lack of cross-sample relational supervision as a key limitation of existing MLLM training paradigms. To address it, we propose a distribution-aware reinforcement learning framework based on Group Relative Policy Optimization, which introduces batch-level comparison-based supervision via the Concordance Correlation Coefficient-based reward to align predicted and ground-truth distributions in terms of correlation, scale, and mean. The framework is plug-and-play, requiring no architectural modification. Experiments on a unified suite of long-tailed regression benchmarks show consistent improvements over SFT and existing MLLM regression methods, with particularly strong gains in medium- and few-shot regimes.

Despite the great advance of Multimodal Large Language Models (MLLMs) in both instruction dataset building and benchmarking, the independence of training and evaluation makes current MLLMs hard to further improve their capability under the guidance of evaluation results with a relatively low human cost. In this paper, we propose MLLM-DataEngine, a novel closed-loop system that bridges data generation, model training, and evaluation. Within each loop iteration, the MLLM-DataEngine first analyze the weakness of the model based on the evaluation results, then generate a proper incremental dataset for the next training iteration and enhance the model capability iteratively. Compared with previous data collection methods which are separate from the benchmarking, the data generated by MLLM-DataEngine shows better targeting, quality, and correctness. For targeting, we propose an Adaptive Bad-case Sampling module, which adjusts the ratio of different types of data within each incremental dataset based on the benchmarking results. For quality, we resort to GPT-4 to generate high-quality data with each given data type. For correctness, prompt design is critical for the data generation results. Rather than previous hand-crafted prompt, we propose an Interactive Prompt Optimization strategy, which optimizes the prompt with the multi-round interaction between human and GPT, and improve the correctness of generated data greatly. Through extensive experiments, we find our MLLM-DataEngine could boost the MLLM capability in a targeted and automatic manner, with only a few human participation. We hope it could be a general solution for the following MLLMs building. The MLLM-DataEngine has been open-sourced and is now available at https://github.com/opendatalab/MLLM-DataEngine.

Multimodal large language models (MLLMs) answer questions about whole images well, yet they still struggle with fine-grained region understanding. A key reason is that text-only supervision never specifies which regions support an answer. To close this gap, we present Xiaomi-Lens-0, a 4B MLLM built on Qwen3.5 that predicts masks from its own visual representations. Specifically, a lightweight decoder combines vision-encoder patch features with visual latents, the language model's mask-token states, so mask supervision reaches the shared backbone without an additional segmentation encoder. Because each latent decodes to a mask, the model can interleave reasoning with region-specific latents and thus think with visual latents, while grounded reasoning traces supervise the regions it visits during chain-of-thought. As a result, across all eight RefCOCO, RefCOCO+, and RefCOCOg splits, Xiaomi-Lens-0 gains 5.6 points on average over Qwen3.5 in referring comprehension and achieves the highest segmentation cIoU among compared models. Moreover, it surpasses Qwen3.5 across all perception benchmarks. Homepage: https://seerray-lab.github.io/Xiaomi-Lens-0{this https URL}

This paper provides a comprehensive survey of the latest research on multilingual large language models (MLLMs). MLLMs not only are able to understand and generate language across linguistic boundaries, but also represent an important advancement in artificial intelligence. We first discuss the architecture and pre-training objectives of MLLMs, highlighting the key components and methodologies that contribute to their multilingual capabilities. We then discuss the construction of multilingual pre-training and alignment datasets, underscoring the importance of data quality and diversity in enhancing MLLM performance. An important focus of this survey is on the evaluation of MLLMs. We present a detailed taxonomy and roadmap covering the assessment of MLLMs' cross-lingual knowledge, reasoning, alignment with human values, safety, interpretability and specialized applications. Specifically, we extensively discuss multilingual evaluation benchmarks and datasets, and explore the use of LLMs themselves as multilingual evaluators. To enhance MLLMs from black to white boxes, we also address the interpretability of multilingual capabilities, cross-lingual transfer and language bias within these models. Finally, we provide a comprehensive review of real-world applications of MLLMs across diverse domains, including biology, medicine, computer science, mathematics and law. We showcase how these models have driven innovation and improvements in these specialized fields while also highlighting the challenges and opportunities in deploying MLLMs within diverse language communities and application scenarios. We listed the paper related in this survey and publicly available at https://github.com/tjunlp-lab/Awesome-Multilingual-LLMs-Papers.

The rapid evolution of Multimodal Large Language Models (MLLMs) has brought substantial advancements in artificial intelligence, significantly enhancing the capability to understand and generate multimodal content. While prior studies have largely concentrated on model architectures and training methodologies, a thorough analysis of the benchmarks used for evaluating these models remains underexplored. This survey addresses this gap by systematically reviewing 211 benchmarks that assess MLLMs across four core domains: understanding, reasoning, generation, and application. We provide a detailed analysis of task designs, evaluation metrics, and dataset constructions, across diverse modalities. We hope that this survey will contribute to the ongoing advancement of MLLM research by offering a comprehensive overview of benchmarking practices and identifying promising directions for future work. An associated GitHub repository collecting the latest papers is available.

Calibrating distributed hydrologic models is a critical bottleneck across operational water resources management - streamflow prediction, reservoir operation, drought monitoring, infrastructure design, and flood forecasting all depend on it. Each basin demands an expert to translate hydrograph signatures into adjustments of a high-dimensional parameter vector, and the resulting workflow does not transfer between watersheds. We ask: can frontier large language model (LLM) agents replace the human hydrologic modeler, and if not, what would it take? We benchmark nine frontier LLM agents - Claude Opus 4.6/4.7, Sonnet 4.6, GPT-5/5.4/5.4-pro, and Gemini 2.5-pro/3.1-pro/3-flash - on the operational CREST distributed hydrologic model used by the U.S. National Weather Service for flash-flood forecasting. Best-of-twenty-rounds Nash-Sutcliffe Efficiency (NSE) across four held-out gauges spanning 329-40,792 km2 ranges from -0.16 (GPT-5.4) to 0.75 (Sonnet 4.6); the ceiling reproduces across all three vendors and capability tiers, with the strongest models concentrating in the 0.65-0.75 band, and no model reaches the human-expert reference except Opus-4.7 on one gauge. We argue this gap is not a parameter-count problem but a domain-grounding problem. We then propose HYDROAGENT, fine-tuning open-weight Qwen3-4B with supervised fine-tuning on 2,576 expert calibration trajectories and Group-Relative Policy Optimization using NSE as a verifiable reward from online CREST simulations - reinforcement learning with simulation feedback (RLSF). For Earth system science, a small domain-tuned policy with simulator-in-the-loop RL is a more compute-efficient and physically faithful path than scaling generic frontier models, and the multi-modal richness of Earth data - remote sensing, in-situ time series, and forecaster narrative - makes domain agents a leveraged direction for AI in physical science.

Frontier LLMs are increasingly put to use on open-ended complex questions, different in nature from the ones they are typically evaluated on. We dedicate more than 4,000 human expert hours to evaluate a selection of six frontier LLMs on a member of this class of problems: EuroExec, our introduced human expert-based benchmark composed of 413 open-ended long-form European executive tasks authored by 47 vetted domain experts, each question drawn from experience in a real case. Every response is manually evaluated through a multi-attribute rubric, an item-specific checklist of requirements, and a preference rank ordering, extracting an aggregate metric "Solve Rate". The strongest model solves only 56.9% of tasks, while expert-written reference answers judged blindly are solved at near-ceiling levels and are preferred over every model response in 74% of direct rankings, placing frontier generative systems well below the professional standard of work they are already used for. We see that the best way to extract this kind of conclusion is by employing human evaluators, carefully checking their consistency through rigorous statistical analysis, and observe that automatic measurements also fall short when evaluating on this case of real-world open-ended problems with a subjective ground truth.

Multi-modal Large Language Models (MLLMs) have shown impressive abilities in generating reasonable responses with respect to multi-modal contents. However, there is still a wide gap between the performance of recent MLLM-based applications and the expectation of the broad public, even though the most powerful OpenAI's GPT-4 and Google's Gemini have been deployed. This paper strives to enhance understanding of the gap through the lens of a qualitative study on the generalizability, trustworthiness, and causal reasoning capabilities of recent proprietary and open-source MLLMs across four modalities: ie, text, code, image, and video, ultimately aiming to improve the transparency of MLLMs. We believe these properties are several representative factors that define the reliability of MLLMs, in supporting various downstream applications. To be specific, we evaluate the closed-source GPT-4 and Gemini and 6 open-source LLMs and MLLMs. Overall we evaluate 230 manually designed cases, where the qualitative results are then summarized into 12 scores (ie, 4 modalities times 3 properties). In total, we uncover 14 empirical findings that are useful to understand the capabilities and limitations of both proprietary and open-source MLLMs, towards more reliable downstream multi-modal applications.

Recently, promising progress has been made by open-source vision-language models (VLMs) in bringing their capabilities closer to those of proprietary frontier models. However, most open-source models only publish their final model weights, leaving the critical details of data strategies and implementation largely opaque. In this work, we address VLM post-training from a data-centric perspective, showing the key role of data strategy in developing frontier VLMs. By studying and building our post-training data strategy from scratch, we share detailed insights into the development processes, aiming to benefit the development of competitive models for the open-source community. Our introduced data strategy, together with training recipes and model design, leads to a family of performant VLMs named Eagle2. Specifically, Eagle2-9B achieves state-of-the-art results across various multimodal benchmarks, matching certain competitive models with up to 70B parameters.

LLM agents are beginning to invoke industrial asset-management tools through the Model Context Protocol (MCP), yet whether they can act reliably on this substrate for safety-critical Prognostics and Health Management (PHM) is unanswered. Prior benchmarks conflate protocol fluency with reasoning, instrumentation failures with agent failures, and tool use with tool retrieval. We introduce PHMForge, an evaluation environment that closes each conflation. PHMForge ships 99 SME-authored scenarios across eight industrial asset classes spanning rotating equipment, aero-engines, and lithium-ion cells, on public datasets including NASA PCoE, served through 39 MCP-native tools wrapping published PHM algorithms (C-MAPSS, ISO~10816, Arrhenius capacity-fade models, time-series foundation models). Krippendorff's αin [0.74,,0.82] on a 30-scenario stratified rotating-equipment/aero-engine sample; the battery extension is single-rater. Across three agentic frameworks and six LLM backbones, the strongest configuration reaches 80.8\% pass@1, with the residual gap concentrated in orchestration and tool-sequencing errors. Crucially, an architectural ablation shows that replacing MCP execution with text-based Retrieval-Augmented Generation (RAG) over telemetry-equivalent evidence collapses Remaining Useful Life pass-all-3 from 100\% to 20\% (5/5 vs.\ 1/5) on the battery class, exposing the structural limits of static retrieval for prognostic computation. Trajectory decomposition shows orchestration errors dominate failures across backbones, while schema-invalid tool calls concentrate in smaller open-weight models. Frontier LLMs are stronger at calling tools than at planning when to call them. PHMForge is open-sourced with deterministic evaluators, a public leaderboard, and a datasheet.

Large language models (LLMs) have been increasingly used in time series analysis. However, the potential of multimodal LLMs (MLLMs), particularly vision-language models, for time series remains largely under-explored. One natural way for humans to detect time series anomalies is through visualization and textual description. Motivated by this, we raise a critical and practical research question: Can multimodal LLMs perform time series anomaly detection? To answer this, we propose VisualTimeAnomaly benchmark to evaluate MLLMs in time series anomaly detection (TSAD). Our approach transforms time series numerical data into the image format and feed these images into various MLLMs, including proprietary models (GPT-4o and Gemini-1.5) and open-source models (LLaVA-NeXT and Qwen2-VL), each with one larger and one smaller variant. In total, VisualTimeAnomaly contains 12.4k time series images spanning 3 scenarios and 3 anomaly granularities with 9 anomaly types across 8 MLLMs. Starting with the univariate case (point- and range-wise anomalies), we extend our evaluation to more practical scenarios, including multivariate and irregular time series scenarios, and variate-wise anomalies. Our study reveals several key insights: 1) MLLMs detect range- and variate-wise anomalies more effectively than point-wise anomalies. 2) MLLMs are highly robust to irregular time series, even with 25% of the data missing. 3) Open-source MLLMs perform comparably to proprietary models in TSAD. While open-source MLLMs excel on univariate time series, proprietary MLLMs demonstrate superior effectiveness on multivariate time series. To the best of our knowledge, this is the first work to comprehensively investigate MLLMs for TSAD, particularly for multivariate and irregular time series scenarios. We release our dataset and code at https://github.com/mllm-ts/VisualTimeAnomaly to support future research.

We ask whether large language models (LLMs) can design effective algorithms for well-specified operations research (OR) problems. We study inventory control, queueing network control, and assortment optimization, using benchmark instances from recent papers in each area. We evaluate two levels of LLM use: at level 1, the model receives one problem instance and returns a solution for that instance; at level 2, it receives only the problem class description and broad parameter ranges, and returns an algorithm that maps instance parameters to solutions. Human input is minimal: we give one untuned prompt that describes the problem, and the model has access to a Python sandbox tool with a fixed compute budget. The strongest model we test, gpt-5.6-sol, matches or outperforms the best method reported in those papers on almost all evaluated instances. This holds even at level 2, where the returned algorithm is fixed before seeing the evaluation instances. Performance also improves sharply across models released less than eight months apart, suggesting that this capability is moving quickly. Thus, for the well-specified operations problems we study, a single untuned LLM query can already produce algorithms competitive with specialized methods. These results suggest that frontier LLMs can be a serious empirical baseline for algorithm design in well-specified OR problems.

The multimodal language models (MLMs) based on generative pre-trained Transformer are considered powerful candidates for unifying various domains and tasks. MLMs developed for remote sensing (RS) have demonstrated outstanding performance in multiple tasks, such as visual question answering and visual grounding. In addition to visual grounding that detects specific objects corresponded to given instruction, aerial detection, which detects all objects of multiple categories, is also a valuable and challenging task for RS foundation models. However, aerial detection has not been explored by existing RS MLMs because the autoregressive prediction mechanism of MLMs differs significantly from the detection outputs. In this paper, we present a simple baseline for applying MLMs to aerial detection for the first time, named LMMRotate. Specifically, we first introduce a normalization method to transform detection outputs into textual outputs to be compatible with the MLM framework. Then, we propose a evaluation method, which ensures a fair comparison between MLMs and conventional object detection models. We construct the baseline by fine-tuning open-source general-purpose MLMs and achieve impressive detection performance comparable to conventional detector. We hope that this baseline will serve as a reference for future MLM development, enabling more comprehensive capabilities for understanding RS images. Code is available at https://github.com/Li-Qingyun/mllm-mmrotate.

Conventional evaluation methods for multimodal LLMs (MLLMs) lack interpretability and are often insufficient to fully disclose significant capability gaps across models. To address this, we introduce AuditDM, an automated framework that actively discovers and rectifies MLLM failure modes by auditing their divergence. AuditDM fine-tunes an MLLM as an auditor via reinforcement learning to generate challenging questions and counterfactual images that maximize disagreement among target models. Once trained, the auditor uncovers diverse, interpretable exemplars that reveal model weaknesses and serve as annotation-free data for rectification. When applied to SoTA models like Gemma-3 and PaliGemma-2, AuditDM discovers more than 20 distinct failure types. Fine-tuning on these discoveries consistently improves all models across 16 benchmarks, and enables a 3B model to surpass its 28B counterpart. Our results suggest that as data scaling hits diminishing returns, targeted model auditing offers an effective path to model diagnosis and improvement.

The rapid advancement of multimodal large language models (LLMs) has opened new frontiers in artificial intelligence, enabling the integration of diverse large-scale data types such as text, images, and spatial information. In this paper, we explore the potential of multimodal LLMs (MLLM) for geospatial artificial intelligence (GeoAI), a field that leverages spatial data to address challenges in domains including Geospatial Semantics, Health Geography, Urban Geography, Urban Perception, and Remote Sensing. We propose a MLLM (OmniGeo) tailored to geospatial applications, capable of processing and analyzing heterogeneous data sources, including satellite imagery, geospatial metadata, and textual descriptions. By combining the strengths of natural language understanding and spatial reasoning, our model enhances the ability of instruction following and the accuracy of GeoAI systems. Results demonstrate that our model outperforms task-specific models and existing LLMs on diverse geospatial tasks, effectively addressing the multimodality nature while achieving competitive results on the zero-shot geospatial tasks. Our code will be released after publication.

Multimodal Large Language Models (mLLMs) are trained on a large amount of text-image data. While most mLLMs are trained on caption-like data only, Alayrac et al. [2022] showed that additionally training them on interleaved sequences of text and images can lead to the emergence of in-context learning capabilities. However, the dataset they used, M3W, is not public and is only in English. There have been attempts to reproduce their results but the released datasets are English-only. In contrast, current multilingual and multimodal datasets are either composed of caption-like only or medium-scale or fully private data. This limits mLLM research for the 7,000 other languages spoken in the world. We therefore introduce mOSCAR, to the best of our knowledge the first large-scale multilingual and multimodal document corpus crawled from the web. It covers 163 languages, 315M documents, 214B tokens and 1.2B images. We carefully conduct a set of filtering and evaluation steps to make sure mOSCAR is sufficiently safe, diverse and of good quality. We additionally train two types of multilingual model to prove the benefits of mOSCAR: (1) a model trained on a subset of mOSCAR and captioning data and (2) a model train on captioning data only. The model additionally trained on mOSCAR shows a strong boost in few-shot learning performance across various multilingual image-text tasks and benchmarks, confirming previous findings for English-only mLLMs.

Large language models (LLMs) are expanding from assisting scientific research and engineering to autonomously developing and improving AI systems, advancing AI for AI (AI4AI) as a pathway toward recursive self-improvement (RSI). Workflow-driven machine learning engineering (MLE) systems provide a practical path toward this pursuit through complex orchestration that manages long-horizon experimentation, while recent MLE systems adopt model-directed interaction, allowing models to autonomously organize experiments and adapt optimization strategies based on execution feedback. However, feedback from each experiment reflects several preceding decisions, and a long MLE run contains many such costly experiments. Training must therefore select useful supervision from long interaction trajectories and learn from intermediate outcomes. We propose a post-training method for autonomous long-horizon MLE optimization and apply it to train MLExpert, a 35B Mixture-of-Experts agentic model. We design the Kaggle-MLE Factory to construct executable tasks and an interaction harness for model-directed experimentation. Hierarchical agentic SFT transfers general tool-use and coding capabilities to MLE through outcome-guided supervision. Windowed Interaction RL (WIRL) treats the multi-turn decisions between successive experiment results as an execution window and assigns it a shared outcome-based reward. Asynchronous collection and policy correction support policy updates before the trajectory ends. On MLE-Bench Lite, MLExpert improves the average medal rate of the base model from 37.9% to 72.7%, achieving performance comparable to larger frontier models such as Kimi-K3 and GLM-5.3. Further experiments show that MLExpert improves performance on NatureBench Lite, agent scaffold optimization, and algorithm optimization, suggesting that the learned optimization capability generalizes to other tasks.

We introduce Meta MLGym and MLGym-Bench, a new framework and benchmark for evaluating and developing LLM agents on AI research tasks. This is the first Gym environment for machine learning (ML) tasks, enabling research on reinforcement learning (RL) algorithms for training such agents. MLGym-bench consists of 13 diverse and open-ended AI research tasks from diverse domains such as computer vision, natural language processing, reinforcement learning, and game theory. Solving these tasks requires real-world AI research skills such as generating new ideas and hypotheses, creating and processing data, implementing ML methods, training models, running experiments, analyzing the results, and iterating through this process to improve on a given task. We evaluate a number of frontier large language models (LLMs) on our benchmarks such as Claude-3.5-Sonnet, Llama-3.1 405B, GPT-4o, o1-preview, and Gemini-1.5 Pro. Our MLGym framework makes it easy to add new tasks, integrate and evaluate models or agents, generate synthetic data at scale, as well as develop new learning algorithms for training agents on AI research tasks. We find that current frontier models can improve on the given baselines, usually by finding better hyperparameters, but do not generate novel hypotheses, algorithms, architectures, or substantial improvements. We open-source our framework and benchmark to facilitate future research in advancing the AI research capabilities of LLM agents.

Multimodal Large Language Models (MLLMs) are strong perceivers of images and video. We ask how far that reach extends into acting: dropping an MLLM directly into a drone's control loop, with its entire action space declared solely in the prompt. Recent systems approach this setting but increasingly narrow the model's decision-making. We widen it back. We introduce DroneCATS-Agent, an architecture where the MLLM is a swappable component, and DroneCATS, a benchmark treating the model as the independent variable. Beyond merely flying toward a pixel, our agent entrusts the model to yaw and search, deliberate when unsure, and self-declare arrival---all without fine-tuning or function-calling schemas. Evaluating frontier and open models across four core capabilities---approaching a visible target, tracking a moving one, searching outside the initial view, and commanding a multi-drone fleet---reveals that even the simplest embodied settings are far from solved. Crucially, to identify what breaks first at the edge, our roster scales down to 2B parameters. The findings expose a stark paradox: it is not the flying that fails. Small open models often navigate into the success radius more reliably than frontier models, yet lose the episode by declaring arrival prematurely or not at all. Multi-drone commanding amplifies this divide, with small models failing by blindly copying a single coordinate across distinct views. Viewed as vision-language-action agents, the models' spatial perception holds up, but their action protocol does not. What separates a deployable edge model from a frontier model is not navigation, but the discipline to sustain a declared protocol and emit the correct terminating action. The open problem is closing this gap at onboard compute costs---yielding a fast model that plans persistently and knows exactly when it is done---and DroneCATS is built to measure that distance.

Based on the foundation of Large Language Models (LLMs), Multilingual Large Language Models (MLLMs) have been developed to address the challenges of multilingual natural language processing tasks, hoping to achieve knowledge transfer from high-resource to low-resource languages. However, significant limitations and challenges still exist, such as language imbalance, multilingual alignment, and inherent bias. In this paper, we aim to provide a comprehensive analysis of MLLMs, delving deeply into discussions surrounding these critical issues. First of all, we start by presenting an overview of MLLMs, covering their evolution, key techniques, and multilingual capacities. Secondly, we explore widely utilized multilingual corpora for MLLMs' training and multilingual datasets oriented for downstream tasks that are crucial for enhancing the cross-lingual capability of MLLMs. Thirdly, we survey the existing studies on multilingual representations and investigate whether the current MLLMs can learn a universal language representation. Fourthly, we discuss bias on MLLMs including its category and evaluation metrics, and summarize the existing debiasing techniques. Finally, we discuss existing challenges and point out promising research directions. By demonstrating these aspects, this paper aims to facilitate a deeper understanding of MLLMs and their potentiality in various domains.

Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in vision-language understanding, reasoning, and generation. However, they struggle with tasks requiring fine-grained localization and reasoning in high-resolution images. This constraint stems from the fact that MLLMs are fine-tuned with fixed image resolution to align with the pre-trained image encoder used in MLLM. Consequently, feeding high-resolution images directly into MLLMs leads to poor generalization due to a train-test resolution discrepancy, while downsampling these images-although ensuring consistency-compromises fine-grained visual details and ultimately degrades performance. To address this challenge, we propose Extract Candidate then Predict (ECP), a novel training-free, task-agnostic two-stage framework designed to enhance MLLM performance on high-resolution images. The key intuition behind ECP is that while MLLMs struggle with high-resolution images, their predictions on downsampled images still contain implicit localization cues. By first identifying candidate region using the coarse prediction and then predicting the final output based on candidate region, ECP effectively preserves fine-grained details while mitigating the challenges posed by high-resolution data. We validate our framework on 4K GUI grounding and 4K, 8K MLLM perception, achieving +21.3%, +5.8%, +5.2% absolute improvement compared to baseline respectively, demonstrating its effectiveness. Code is available at https://github.com/yenncye/ECP.

Multi-modal large language models (MLLMs) have demonstrated remarkable vision-language capabilities, primarily due to the exceptional in-context understanding and multi-task learning strengths of large language models (LLMs). The advent of visual instruction tuning has further enhanced MLLMs' performance in vision-language understanding. However, while existing MLLMs adeptly recognize what objects are in an image, they still face challenges in effectively discerning where these objects are, particularly along the distance (scene depth) axis. To overcome this limitation in MLLMs, we introduce Proximity Question Answering (Proximity QA), a novel framework designed to enable MLLMs to infer the proximity relationship between objects in images. The framework operates in two phases: the first phase focuses on guiding the models to understand the relative depth of objects, and the second phase further encourages the models to infer the proximity relationships between objects based on their depth perceptions. We also propose a VQA dataset called Proximity-110K, containing additional instructions that incorporate depth information and the proximity relationships of objects. We have conducted extensive experiments to validate Proximity QA's superior ability in depth perception and proximity analysis, outperforming other state-of-the-art MLLMs. Code and dataset will be released at magenta{https://github.com/NorthSummer/ProximityQA.git}.

Endoscopic procedures are essential for diagnosing and treating internal diseases, and multi-modal large language models (MLLMs) are increasingly applied to assist in endoscopy analysis. However, current benchmarks are limited, as they typically cover specific endoscopic scenarios and a small set of clinical tasks, failing to capture the real-world diversity of endoscopic scenarios and the full range of skills needed in clinical workflows. To address these issues, we introduce EndoBench, the first comprehensive benchmark specifically designed to assess MLLMs across the full spectrum of endoscopic practice with multi-dimensional capacities. EndoBench encompasses 4 distinct endoscopic scenarios, 12 specialized clinical tasks with 12 secondary subtasks, and 5 levels of visual prompting granularities, resulting in 6,832 rigorously validated VQA pairs from 21 diverse datasets. Our multi-dimensional evaluation framework mirrors the clinical workflow--spanning anatomical recognition, lesion analysis, spatial localization, and surgical operations--to holistically gauge the perceptual and diagnostic abilities of MLLMs in realistic scenarios. We benchmark 23 state-of-the-art models, including general-purpose, medical-specialized, and proprietary MLLMs, and establish human clinician performance as a reference standard. Our extensive experiments reveal: (1) proprietary MLLMs outperform open-source and medical-specialized models overall, but still trail human experts; (2) medical-domain supervised fine-tuning substantially boosts task-specific accuracy; and (3) model performance remains sensitive to prompt format and clinical task complexity. EndoBench establishes a new standard for evaluating and advancing MLLMs in endoscopy, highlighting both progress and persistent gaps between current models and expert clinical reasoning. We publicly release our benchmark and code.

Current Multimodal Large Language Models exhibit very strong performance for several demanding tasks. While commercial MLLMs deliver acceptable performance in low-resource languages, comparable results remain unattained within the open science community. In this paper, we aim to develop a strong MLLM for a low-resource language, namely Basque. For that purpose, we develop our own training and evaluation image-text datasets. Using two different Large Language Models as backbones, the Llama-3.1-Instruct model and a Basque-adapted variant called Latxa, we explore several data mixtures for training. We show that: i) low ratios of Basque multimodal data (around 20%) are already enough to obtain solid results on Basque benchmarks, and ii) contrary to expected, a Basque instructed backbone LLM is not required to obtain a strong MLLM in Basque. Our results pave the way to develop MLLMs for other low-resource languages by openly releasing our resources.

The success of Large Language Models (LLM) has led researchers to explore Multimodal Large Language Models (MLLM) for unified visual and linguistic understanding. However, the increasing model size and computational complexity of MLLM limit their use in resource-constrained environments. Small-scale MLLM (s-MLLM) aims to retain the capabilities of the large-scale model (l-MLLM) while reducing computational demands, but resulting in a significant decline in performance. To address the aforementioned issues, we propose a novel LLaVA-KD framework to transfer knowledge from l-MLLM to s-MLLM. Specifically, we introduce Multimodal Distillation (MDist) to minimize the divergence between the visual-textual output distributions of l-MLLM and s-MLLM, and Relation Distillation (RDist) to transfer l-MLLM's ability to model correlations between visual features. Additionally, we propose a three-stage training scheme to fully exploit the potential of s-MLLM: 1) Distilled Pre-Training to align visual-textual representations, 2) Supervised Fine-Tuning to equip the model with multimodal understanding, and 3) Distilled Fine-Tuning to further transfer l-MLLM capabilities. Our approach significantly improves performance without altering the small model's architecture. Extensive experiments and ablation studies validate the effectiveness of each proposed component. Code will be available at https://github.com/caiyuxuan1120/LLaVA-KD.

Expanding the long-context capabilities of Multi-modal Large Language Models~(MLLMs) is crucial for video understanding, high-resolution image understanding, and multi-modal agents. This involves a series of systematic optimizations, including model architecture, data construction and training strategy, particularly addressing challenges such as degraded performance with more images and high computational costs. In this paper, we adapt the model architecture to a hybrid of Mamba and Transformer blocks, approach data construction with both temporal and spatial dependencies among multiple images and employ a progressive training strategy. The released model LongLLaVA~(Long-Context Large Language and Vision Assistant) is the first hybrid MLLM, which achieved a better balance between efficiency and effectiveness. LongLLaVA not only achieves competitive results across various benchmarks, but also maintains high throughput and low memory consumption. Especially, it could process nearly a thousand images on a single A100 80GB GPU, showing promising application prospects for a wide range of tasks.

The deployment of Multimodal Large Language Models (MLLMs) in agriculture is currently stalled by a critical trade-off: the existing literature lacks the large-scale agricultural datasets required for robust model development and evaluation, while current state-of-the-art models lack the verified domain expertise necessary to reason across diverse taxonomies. To address these challenges, we propose the Vision-to-Verified-Knowledge (V2VK) pipeline, a novel generative AI-driven annotation framework that integrates visual captioning with web-augmented scientific retrieval to autonomously generate the AgriMM benchmark, effectively eliminating biological hallucinations by grounding training data in verified phytopathological literature. The AgriMM benchmark contains over 3,000 agricultural classes and more than 607k VQAs spanning multiple tasks, including fine-grained plant species identification, plant disease symptom recognition, crop counting, and ripeness assessment. Leveraging this verifiable data, we present AgriChat, a specialized MLLM that presents broad knowledge across thousands of agricultural classes and provides detailed agricultural assessments with extensive explanations. Extensive evaluation across diverse tasks, datasets, and evaluation conditions reveals both the capabilities and limitations of current agricultural MLLMs, while demonstrating AgriChat's superior performance over other open-source models, including internal and external benchmarks. The results validate that preserving visual detail combined with web-verified knowledge constitutes a reliable pathway toward robust and trustworthy agricultural AI. The code and dataset are publicly available at https://github.com/boudiafA/AgriChat .

Time series question-answering (TSQA), in which we ask natural language questions to infer and reason about properties of time series, is a promising yet underexplored capability of foundation models. In this work, we present ARFBench, a TSQA benchmark that evaluates the understanding of multimodal foundation models (FMs) on time series anomalies prevalent in software incident data. ARFBench consists of 750 questions across 142 time series and 5.38M data points from 63 production incidents sourced exclusively from internal telemetry at Datadog. We evaluate leading proprietary and open-source LLMs, VLMs, and time series FMs and observe that frontier VLMs perform markedly better than existing baselines; the leading model (GPT-5) achieves a 62.7% accuracy and 51.9% F1. We next demonstrate the promise of specialized multimodal approaches. We develop a novel TSFM + VLM hybrid prototype which we post-train on a small set of synthetic and real data that yields comparable overall F1 and accuracy with frontier models. Lastly, we find models and human domain experts exhibit complementary strengths. We define a model-expert oracle, a best-of-2 oracle selector over model and expert answers, yielding 82.8% F1 and 87.2% accuracy and establishing a new superhuman frontier for future TSQA models. The benchmark is available at https://huggingface.co/datasets/Datadog/ARFBench.

By integrating the perception capabilities of multimodal encoders with the generative power of Large Language Models (LLMs), Multimodal Large Language Models (MLLMs), exemplified by GPT-4V, have achieved great success in various multimodal tasks, pointing toward a promising pathway to artificial general intelligence. Despite this progress, the limited quality of multimodal data, poor performance on many complex downstream tasks, and inadequate evaluation protocols continue to hinder the reliability and broader applicability of MLLMs across diverse domains. Inspired by the human ability to leverage external tools for enhanced reasoning and problem-solving, augmenting MLLMs with external tools (e.g., APIs, expert models, and knowledge bases) offers a promising strategy to overcome these challenges. In this paper, we present a comprehensive survey on leveraging external tools to enhance MLLM performance. Our discussion is structured along four key dimensions about external tools: (1) how they can facilitate the acquisition and annotation of high-quality multimodal data; (2) how they can assist in improving MLLM performance on challenging downstream tasks; (3) how they enable comprehensive and accurate evaluation of MLLMs; (4) the current limitations and future directions of tool-augmented MLLMs. Through this survey, we aim to underscore the transformative potential of external tools in advancing MLLM capabilities, offering a forward-looking perspective on their development and applications. The project page of this paper is publicly available athttps://github.com/Lackel/Awesome-Tools-for-MLLMs.

As models scale, reward hacking becomes more frequent, more sophisticated, and more consequential. Does it leave a telltale signature in model representations? This work analyzes how reward hacking is represented internally in frontier open source LLMs, and how those representations can be used to understand and discover the range of hacking behaviors a model displays. In particular, we find that simple difference of means vectors coherently represent reward hacking in Kimi K3, GLM 5.2, and Qwen 3.8 Max across a variety of behaviors in common evaluations. Despite their simplicity, these vectors are both generalizable and interpretable, and we can use them to reliably detect reward hacking. We first evaluate reward hacking in commonly reported benchmarks like DeepSWE and SWE-bench, finding that models reward hack excessively in these environments; GLM 5.2 hacks in 57.2% of rollouts on DeepSWE and in 73% of rollouts on SWE-bench. Catching these requires monitors; LLM monitors are effective, but expensive detectors. We show that DoM vectors are similarly effective but virtually free, catching 3.1% more hacks in Kimi K3 and 7.9% fewer hacks in GLM 5.2 on DeepSWE at a monitor matched false positive rate. DoM vectors run on the chain-of-thought also predict reward hacks in the model's subsequent actions, meaning we can run them online and catch potential hacks before they occur. Finally, we analyze probe-hits that LLM monitors do not catch and discover other undesirable behaviors, as well as show transfer to finding hacks in non-SWE evaluations. Together, these results provide evidence that simple, white-box methods can be used to scalably study and monitor reward hacking behaviors in frontier open source models

As the research of Multimodal Large Language Models (MLLMs) becomes popular, an advancing MLLM model is typically required to handle various textual and visual tasks (e.g., VQA, Detection, OCR, and ChartQA) simultaneously for real-world applications. However, due to the significant differences in representation and distribution among data from various tasks, simply mixing data of all tasks together leads to the well-known``multi-task conflict" issue, resulting in performance degradation across various tasks. To address this issue, we propose Awaker2.5-VL, a Mixture of Experts~(MoE) architecture suitable for MLLM, which acquires the multi-task capabilities through multiple sparsely activated experts. To speed up the training and inference of Awaker2.5-VL, each expert in our model is devised as a low-rank adaptation (LoRA) structure. Extensive experiments on multiple latest benchmarks demonstrate the effectiveness of Awaker2.5-VL. The code and model weight are released in our Project Page: https://github.com/MetabrainAGI/Awaker.

The surge of LLM studies makes synthesizing their findings challenging. Meta-analysis can uncover important trends across studies, but its use is limited by the time-consuming nature of manual data extraction. Our study presents a semi-automated approach for meta-analysis that accelerates data extraction using LLMs. It automatically identifies relevant arXiv papers, extracts experimental results and related attributes, and organizes them into a structured dataset. We conduct a comprehensive meta-analysis of frontier LLMs using an automatically extracted dataset, reducing the effort of paper surveying and data extraction by more than 93\% compared to manual approaches. We validate our dataset by showing that it reproduces key findings from a recent manual meta-analysis about Chain-of-Thought (CoT), and also uncovers new insights that go beyond it, showing for example that in-context examples benefit multimodal tasks but offer limited gains in mathematical tasks compared to CoT. Our automatically updatable dataset enables continuous tracking of target models by extracting evaluation studies as new data becomes available. Through our scientific artifacts and empirical analysis, we provide novel insights into LLMs while facilitating ongoing meta-analyses of their behavior.

The revolutionary capabilities of large language models (LLMs) have paved the way for multimodal large language models (MLLMs) and fostered diverse applications across various specialized domains. In the remote sensing (RS) field, however, the diverse geographical landscapes and varied objects in RS imagery are not adequately considered in recent MLLM endeavors. To bridge this gap, we construct a large-scale RS image-text dataset, LHRS-Align, and an informative RS-specific instruction dataset, LHRS-Instruct, leveraging the extensive volunteered geographic information (VGI) and globally available RS images. Building on this foundation, we introduce LHRS-Bot, an MLLM tailored for RS image understanding through a novel multi-level vision-language alignment strategy and a curriculum learning method. Additionally, we introduce LHRS-Bench, a benchmark for thoroughly evaluating MLLMs' abilities in RS image understanding. Comprehensive experiments demonstrate that LHRS-Bot exhibits a profound understanding of RS images and the ability to perform nuanced reasoning within the RS domain.

The discipline of physics stands as a cornerstone of human intellect, driving the evolution of technology and deepening our understanding of the fundamental principles of the cosmos. Contemporary literature includes some works centered on the task of solving physics problems - a crucial domain of natural language reasoning. In this paper, we evaluate the performance of frontier LLMs in solving physics problems, both mathematical and descriptive. We also employ a plethora of inference-time techniques and agentic frameworks to improve the performance of the models. This includes the verification of proposed solutions in a cumulative fashion by other, smaller LLM agents, and we perform a comparative analysis of the performance that the techniques entail. There are significant improvements when the multi-agent framework is applied to problems that the models initially perform poorly on. Furthermore, we introduce a new evaluation benchmark for physics problems, {rm P{small HYSICS}E{small VAL}}, consisting of 19,609 problems sourced from various physics textbooks and their corresponding correct solutions scraped from physics forums and educational websites. Our code and data are publicly available at https://github.com/areebuzair/PhysicsEval.

Frontier LLMs can navigate complex websites, but their cost and reliance on third-party APIs make local deployment impractical. We introduce Agent-as-Annotators, a framework that structures synthetic trajectory generation for web agents by analogy to human annotation roles, replacing the Task Designer, Annotator, and Supervisor with modular LLM components. Using Gemini 3 Pro as teacher, we generate 3,000 trajectories across six web environments and fine-tune a 9B-parameter student with pure supervised learning on the 2,322 that pass quality filtering. The resulting model achieves 41.5% on WebArena, surpassing closed-source models such as Claude 3.5 Sonnet (36.0%) and GPT-4o (31.5%) under the same evaluation protocol, and nearly doubling the previous best open-weight result (Go-Browse, 21.7%). Capabilities transfer to unseen environments, with an 18.2 percentage point gain on WorkArena L1 (an enterprise platform never seen during training) and consistent improvements across three additional benchmarks. Ablations confirm that each pipeline component contributes meaningfully, with Judge filtering, evaluation hints, and reasoning traces each accounting for measurable gains. These results demonstrate that structured trajectory synthesis from a single frontier teacher is sufficient to produce competitive, locally deployable web agents. Project page: https://agent-as-annotators.github.io

In recent years, large language models have had a very impressive performance, which largely contributed to the development and application of artificial intelligence, and the parameters and performance of the models are still growing rapidly. In particular, multimodal large language models (MLLM) can combine multiple modalities such as pictures, videos, sounds, texts, etc., and have great potential in various tasks. However, most MLLMs require very high computational resources, which is a major challenge for most researchers and developers. In this paper, we explored the utility of small-scale MLLMs and applied small-scale MLLMs to the field of autonomous driving. We hope that this will advance the application of MLLMs in real-world scenarios.

We present a system using Multimodal LLMs (MLLMs) to analyze a large database with tens of millions of images captured at different times, with the aim of discovering patterns in temporal changes. Specifically, we aim to capture frequent co-occurring changes ("trends") across a city over a certain period. Unlike previous visual analyses, our analysis answers open-ended queries (e.g., "what are the frequent types of changes in the city?") without any predetermined target subjects or training labels. These properties cast prior learning-based or unsupervised visual analysis tools unsuitable. We identify MLLMs as a novel tool for their open-ended semantic understanding capabilities. Yet, our datasets are four orders of magnitude too large for an MLLM to ingest as context. So we introduce a bottom-up procedure that decomposes the massive visual analysis problem into more tractable sub-problems. We carefully design MLLM-based solutions to each sub-problem. During experiments and ablation studies with our system, we find it significantly outperforms baselines and is able to discover interesting trends from images captured in large cities (e.g., "addition of outdoor dining,", "overpass was painted blue," etc.). See more results and interactive demos at https://boyangdeng.com/visual-chronicles.

The use of Multimodal Large Language Models (MLLMs) as an end-to-end solution for Embodied AI and Autonomous Driving has become a prevailing trend. While MLLMs have been extensively studied for visual semantic understanding tasks, their ability to perform precise and quantitative spatial-temporal understanding in real-world applications remains largely unexamined, leading to uncertain prospects. To evaluate models' Spatial-Temporal Intelligence, we introduce STI-Bench, a benchmark designed to evaluate MLLMs' spatial-temporal understanding through challenging tasks such as estimating and predicting the appearance, pose, displacement, and motion of objects. Our benchmark encompasses a wide range of robot and vehicle operations across desktop, indoor, and outdoor scenarios. The extensive experiments reveals that the state-of-the-art MLLMs still struggle in real-world spatial-temporal understanding, especially in tasks requiring precise distance estimation and motion analysis.

MLLMs MLLMs are beginning to appear in clinical workflows, but their ability to perform complex medical reasoning remains unclear. We present Med-CMR, a fine-grained Medical Complex Multimodal Reasoning benchmark. Med-CMR distinguishes from existing counterparts by three core features: 1) Systematic capability decomposition, splitting medical multimodal reasoning into fine-grained visual understanding and multi-step reasoning to enable targeted evaluation; 2) Challenging task design, with visual understanding across three key dimensions (small-object detection, fine-detail discrimination, spatial understanding) and reasoning covering four clinically relevant scenarios (temporal prediction, causal reasoning, long-tail generalization, multi-source integration); 3) Broad, high-quality data coverage, comprising 20,653 Visual Question Answering (VQA) pairs spanning 11 organ systems and 12 imaging modalities, validated via a rigorous two-stage (human expert + model-assisted) review to ensure clinical authenticity. We evaluate 18 state-of-the-art MLLMs with Med-CMR, revealing GPT-5 as the top-performing commercial model: 57.81 accuracy on multiple-choice questions (MCQs) and a 48.70 open-ended score, outperforming Gemini 2.5 Pro (49.87 MCQ accuracy, 45.98 open-ended score) and leading open-source model Qwen3-VL-235B-A22B (49.34 MCQ accuracy, 42.62 open-ended score). However, specialized medical MLLMs do not reliably outperform strong general models, and long-tail generalization emerges as the dominant failure mode. Med-CMR thus provides a stress test for visual-reasoning integration and rare-case robustness in medical MLLMs, and a rigorous yardstick for future clinical systems.

Multimodal large language models (MLLMs) must balance local detail against scene context when interpreting ultra-high-resolution (UHR) remote sensing (RS) imagery within a limited visual-input budget. Existing selection-based methods either prune tokens and select patches through relevance scoring, or crop actively through repeated inspection. Neither strategy directly redistributes pixels within a continuous full-scene view: the first retains selected tokens or patches, and the second re-encodes a crop detached from its surroundings. Our pilot study finds that a frozen MLLM already produces useful question-guided spatial requests, yet crop-based inspection of the selected regions does not consistently improve its answers. We therefore formulate UHR understanding as a question of where to spend a fixed pixel budget. Based on this, we introduce GazeEarth, a simple-yet-effective training-free framework that couples question-guided region selection with full-scene foveated observation. The MLLM selects evidence cells from an indexed overview; a deterministic, topology-preserving warp resamples the original image onto a fixed-size canvas, enlarging their shared neighborhood while compressing the periphery; the same frozen model answers from this focused view, using at most two MLLM calls and no external selector or iterative search. Across three UHR remote sensing benchmarks and four frozen backbones, GazeEarth improves benchmark-averaged accuracy by 4.6 to 9.4 percentage points over direct answering and 3.4 to 4.3 over overview answering, outperforming task-trained methods. Our analyses show that existing MLLMs can guide where to look in UHR images on their own, and that what they can infer from the selected evidence depends on how that evidence is presented.

Multimodal Large Language Models (MLLMs) have shown promise in a broad range of vision-language tasks with their strong reasoning and generalization capabilities. However, they heavily depend on high-quality data in the Supervised Fine-Tuning (SFT) phase. The existing approaches aim to curate high-quality data via GPT-4V, but they are not scalable due to the commercial nature of GPT-4V and the simplicity of the prompts used to instruct the model. To this end, we devised the FullAnno system, which is a data engine that can generate large-scale, high-quality, and fine-grained image annotations consisting of the category and position of objects, region descriptions, text information, as well as image dense captions. This engine is characterized by its cascade annotation process, which involves multiple expert models and employs rich prompts to instruct LLMs in generating dense image captions. We re-annotated the COCO and Visual Genome datasets using our FullAnno system, tripling the number of object annotations and increasing the length of the original image captions by a factor of 15. Experiments show that the regenerated annotation can significantly enhance the capabilities of LLaVA-v1.5 on several benchmarks. The re-annotated data are available at: https://arcana-project-page.github.io

The rapid advancement of Multimodal Large Language Models (MLLMs) has significantly impacted various multimodal tasks. However, these models face challenges in tasks that require spatial understanding within 3D environments. Efforts to enhance MLLMs, such as incorporating point cloud features, have been made, yet a considerable gap remains between the models' learned representations and the inherent complexity of 3D scenes. This discrepancy largely stems from the training of MLLMs on predominantly 2D data, which restricts their effectiveness in comprehending 3D spaces. To address this issue, in this paper, we propose a novel generalist model, i.e., Video-3D LLM, for 3D scene understanding. By treating 3D scenes as dynamic videos and incorporating 3D position encoding into these representations, our Video-3D LLM aligns video representations with real-world spatial contexts more accurately. Additionally, we have implemented a maximum coverage sampling technique to optimize the balance between computational costs and performance efficiency. Extensive experiments demonstrate that our model achieves state-of-the-art performance on several 3D scene understanding benchmarks, including ScanRefer, Multi3DRefer, Scan2Cap, ScanQA, and SQA3D.

Frontier large language models (LLMs) safety evaluation has largely treated harmful generation as an attack outcome rather than as an object of analysis. Consequently, little is known about the harmful outputs produced during model misbehavior, partly because large-scale, high-quality collections of frontier-LLM misbehavior are difficult to obtain. To address this gap, we introduce HarmProfile, a content-centric benchmark dataset that collects model misbehavior across diverse harm categories and model families, and defines the resulting harmful-output distribution as a model-level risk profile. The premise is that, just as linguistic behavior can be characterized from an utterance corpus, model risk can be characterized from the content, severity, and variation of its safety failures. HarmProfile contains over 80,000 validated artifacts from 23 frontier LLMs across 13 model families, organized into 15 harm categories and 57 subcategories. Using this corpus, we find that frontier LLMs reliably produce harmful content at scale, yet exhibit distinct risk profiles; both harmfulness and diversity grow with model capability, suggesting that frontier LLMs may appear safe yet harbor increasingly dangerous knowledge beneath the alignment surface. Our source code is available at https://github.com/fresh-ma/HarmProfile .

The emergence and growing popularity of multimodal large language models (MLLMs) have significant potential to enhance various aspects of daily life, from improving communication to facilitating learning and problem-solving. Mobile phones, as essential daily companions, represent the most effective and accessible deployment platform for MLLMs, enabling seamless integration into everyday tasks. However, deploying MLLMs on mobile phones presents challenges due to limitations in memory size and computational capability, making it difficult to achieve smooth and real-time processing without extensive optimization. In this paper, we present BlueLM-V-3B, an algorithm and system co-design approach specifically tailored for the efficient deployment of MLLMs on mobile platforms. To be specific, we redesign the dynamic resolution scheme adopted by mainstream MLLMs and implement system optimization for hardware-aware deployment to optimize model inference on mobile phones. BlueLM-V-3B boasts the following key highlights: (1) Small Size: BlueLM-V-3B features a language model with 2.7B parameters and a vision encoder with 400M parameters. (2) Fast Speed: BlueLM-V-3B achieves a generation speed of 24.4 token/s on the MediaTek Dimensity 9300 processor with 4-bit LLM weight quantization. (3) Strong Performance: BlueLM-V-3B has attained the highest average score of 66.1 on the OpenCompass benchmark among models with leq 4B parameters and surpassed a series of models with much larger parameter sizes (e.g., MiniCPM-V-2.6, InternVL2-8B).

Recent advances in multimodal large language models (MLLMs) have demonstrated impressive results in various visual tasks. However, in remote sensing (RS), high resolution and small proportion of objects pose challenges to existing MLLMs, which struggle with object-centric tasks, particularly in precise localization and fine-grained attribute description for each object. These RS MLLMs have not yet surpassed classical visual perception models, as they only provide coarse image understanding, leading to limited gains in real-world scenarios. To address this gap, we establish EagleVision, an MLLM tailored for remote sensing that excels in object detection and attribute comprehension. Equipped with the Attribute Disentangle module, EagleVision learns disentanglement vision tokens to express distinct attributes. To support object-level visual-language alignment, we construct EVAttrs-95K, the first large-scale object attribute understanding dataset in RS for instruction tuning, along with a novel evaluation benchmark, EVBench. EagleVision achieves state-of-the-art performance on both fine-grained object detection and object attribute understanding tasks, highlighting the mutual promotion between detection and understanding capabilities in MLLMs. The code, model, data, and demo will be available at https://github.com/XiangTodayEatsWhat/EagleVision.

The recent surge of Multimodal Large Language Models (MLLMs) has fundamentally reshaped the landscape of AI research and industry, shedding light on a promising path toward the next AI milestone. However, significant challenges remain preventing MLLMs from being practical in real-world applications. The most notable challenge comes from the huge cost of running an MLLM with a massive number of parameters and extensive computation. As a result, most MLLMs need to be deployed on high-performing cloud servers, which greatly limits their application scopes such as mobile, offline, energy-sensitive, and privacy-protective scenarios. In this work, we present MiniCPM-V, a series of efficient MLLMs deployable on end-side devices. By integrating the latest MLLM techniques in architecture, pretraining and alignment, the latest MiniCPM-Llama3-V 2.5 has several notable features: (1) Strong performance, outperforming GPT-4V-1106, Gemini Pro and Claude 3 on OpenCompass, a comprehensive evaluation over 11 popular benchmarks, (2) strong OCR capability and 1.8M pixel high-resolution image perception at any aspect ratio, (3) trustworthy behavior with low hallucination rates, (4) multilingual support for 30+ languages, and (5) efficient deployment on mobile phones. More importantly, MiniCPM-V can be viewed as a representative example of a promising trend: The model sizes for achieving usable (e.g., GPT-4V) level performance are rapidly decreasing, along with the fast growth of end-side computation capacity. This jointly shows that GPT-4V level MLLMs deployed on end devices are becoming increasingly possible, unlocking a wider spectrum of real-world AI applications in the near future.

In this work, we investigate extending the comprehension of Multi-modal Large Language Models (MLLMs) to regional objects. To this end, we propose to extract features corresponding to regional objects as soft prompts for LLM, which provides a straightforward and scalable approach and eliminates the need for LLM fine-tuning. To effectively extract regional features from regular image features and irregular point cloud features, we present a novel and unified position-assisted feature extraction module. Furthermore, training an MLLM from scratch is highly time-consuming. Thus, we propose incrementally extending existing pre-trained MLLMs to comprehend more modalities and the regional objects of those modalities. Specifically, we freeze the Q-Former from BLIP-2, an impressive MLLM, and optimize the modality-specific Lora parameters in Q-Former and LLM for each newly introduced modality. The freezing of the Q-Former eliminates the need for extensive pre-training on massive image-text data. The freezed Q-Former pre-trained from massive image-text data is also beneficial for the pre-training on image-region-text data. We name our framework RegionBLIP. We pre-train RegionBLIP on image-region-text, point-cloud-text, and point-cloud-region-text data. Experimental results verify that can preserve the image comprehension capability of BILP-2 and further gain a comprehension of the newly introduced point cloud modality and regional objects. The Data, Code, and Pre-trained models will be available at https://github.com/mightyzau/RegionBLIP.

Multimodal large language models (MLLMs) are broadly empowering various fields. Despite their advancements, the explainability of MLLMs remains less explored, hindering deeper understanding, model credibility, and effective visualization. Unlike conventional vision models (e.g., CNNs, ViTs, CLIP) that produce a single output, MLLMs generate sequences of tokens progressively, where each generated token depends on the previous context. Therefore, earlier context tokens can introduce redundant activations that interfere with the explanation of later tokens beyond their original information. Existing studies often overlook this issue, but our observations reveal that these redundant correlations can significantly hurt the reliability of explanations. To address this, we propose an estimated causal inference method to mitigate the interference of context to achieve high-quality MLLM explanation, with a novel rank Gaussian filter to further reduce activation noises. We term this method Token Activation Map (TAM) to highlight the consideration of interactions between tokens. TAM also indicates that it excels at explaining multiple tokens of MLLM, which is different from the Class Activation Map (CAM) for a single prediction. Our TAM method significantly outperforms existing SoTA methods, showcasing high-quality visualization results that can be utilized for various scenarios, such as object localization, failure case analysis, video visualization, MLLMs visual comparison, and model understanding (e.g., color, shape, action, location, visual reasoning, multi-turn conversation, etc). The code is available atgithub.com/xmed-lab/TAM.

Multimodal Large Language Models (MLLMs) hold significant promise for revolutionizing traditional education and reducing teachers' workload. However, accurately interpreting unconstrained STEM student handwritten solutions with intertwined mathematical formulas, diagrams, and textual reasoning poses a significant challenge due to the lack of authentic and domain-specific benchmarks. Additionally, current evaluation paradigms predominantly rely on the outcomes of downstream tasks (e.g., auto-grading), which often probe only a subset of the recognized content, thereby failing to capture the MLLMs' understanding of complex handwritten logic as a whole. To bridge this gap, we release EDU-CIRCUIT-HW, a dataset consisting of 1,300+ authentic student handwritten solutions from a university-level STEM course. Utilizing the expert-verified verbatim transcriptions and grading reports of student solutions, we simultaneously evaluate various MLLMs' upstream recognition fidelity and downstream auto-grading performance. Our evaluation uncovers an astonishing scale of latent failures within MLLM-recognized student handwritten content, highlighting the models' insufficient reliability for auto-grading and other understanding-oriented applications in high-stakes educational settings. As a potential solution, we present a case study demonstrating that leveraging identified error patterns to preemptively detect and correct recognition errors, while requiring only minimal human intervention (e.g., routing 3.3% of assignments to human graders and the remainder to the GPT-5.1 grader), can effectively enhance the robustness of the deployed AI-enabled grading system. Code and dataset are available in this GitHub repo: https://gt-learning-innovation.github.io/CIRCUIT_EDU_HW_ACL.

Multimodal Large Language Models (MLLMs) hold promise for accelerating scientific discovery by interpreting complex experimental procedures. However, their true capabilities are poorly understood, as existing benchmarks neglect the fine-grained and long-horizon nature of authentic laboratory work, especially in wet-lab settings. To bridge this gap, we introduce ExpVid, the first benchmark designed to systematically evaluate MLLMs on scientific experiment videos. Curated from peer-reviewed video publications, ExpVid features a new three-level task hierarchy that mirrors the scientific process: (1) Fine-grained Perception of tools, materials, and actions; (2) Procedural Understanding of step order and completeness; and (3) Scientific Reasoning that connects the full experiment to its published conclusions. Our vision-centric annotation pipeline, combining automated generation with multi-disciplinary expert validation, ensures that tasks require visual grounding. We evaluate 19 leading MLLMs on ExpVid and find that while they excel at coarse-grained recognition, they struggle with disambiguating fine details, tracking state changes over time, and linking experimental procedures to scientific outcomes. Our results reveal a notable performance gap between proprietary and open-source models, particularly in high-order reasoning. ExpVid not only provides a diagnostic tool but also charts a roadmap for developing MLLMs capable of becoming trustworthy partners in scientific experimentation.

As a prominent direction of Artificial General Intelligence (AGI), Multimodal Large Language Models (MLLMs) have garnered increased attention from both industry and academia. Building upon pre-trained LLMs, this family of models further develops multimodal perception and reasoning capabilities that are impressive, such as writing code given a flow chart or creating stories based on an image. In the development process, evaluation is critical since it provides intuitive feedback and guidance on improving models. Distinct from the traditional train-eval-test paradigm that only favors a single task like image classification, the versatility of MLLMs has spurred the rise of various new benchmarks and evaluation methods. In this paper, we aim to present a comprehensive survey of MLLM evaluation, discussing four key aspects: 1) the summarised benchmarks types divided by the evaluation capabilities, including foundation capabilities, model self-analysis, and extented applications; 2) the typical process of benchmark counstruction, consisting of data collection, annotation, and precautions; 3) the systematic evaluation manner composed of judge, metric, and toolkit; 4) the outlook for the next benchmark. This work aims to offer researchers an easy grasp of how to effectively evaluate MLLMs according to different needs and to inspire better evaluation methods, thereby driving the progress of MLLM research.

Comprehensive evaluation of Multimodal Large Language Models (MLLMs) has recently garnered widespread attention in the research community. However, we observe that existing benchmarks present several common barriers that make it difficult to measure the significant challenges that models face in the real world, including: 1) small data scale leads to a large performance variance; 2) reliance on model-based annotations results in restricted data quality; 3) insufficient task difficulty, especially caused by the limited image resolution. To tackle these issues, we introduce MME-RealWorld. Specifically, we collect more than 300K images from public datasets and the Internet, filtering 13,366 high-quality images for annotation. This involves the efforts of professional 25 annotators and 7 experts in MLLMs, contributing to 29,429 question-answer pairs that cover 43 subtasks across 5 real-world scenarios, extremely challenging even for humans. As far as we know, MME-RealWorld is the largest manually annotated benchmark to date, featuring the highest resolution and a targeted focus on real-world applications. We further conduct a thorough evaluation involving 28 prominent MLLMs, such as GPT-4o, Gemini 1.5 Pro, and Claude 3.5 Sonnet. Our results show that even the most advanced models struggle with our benchmarks, where none of them reach 60% accuracy. The challenges of perceiving high-resolution images and understanding complex real-world scenarios remain urgent issues to be addressed. The data and evaluation code are released at https://mme-realworld.github.io/ .

Using a zoom-in tool is an important foundational part of modern visual agents, because it allows to efficiently handle tasks involving high-resolution images. Most previous methods need an extensive warm-start supervised fine-tuning phase for teaching models zoom-in. We show that this is not necessary by proposing a new intrinsic reward for learning tool use in MLLMs without the need for additional labels or warm-start SFT. Our InfoNCE-style reward uses a curriculum of increasingly hard negative tool calls as a contrastive training signal. Empirical experiments on V^*, HRBench and MME-RealWorld show that our approach is competitive while being more efficient. When used as a drop-in replacement for SFT, we even outperform all baselines. To directly measure the zoom-in ability of models, we further introduce the scalable synthetic Muffin&Chihuahua (M&C) dataset. Each image consists of a grid with every cell either showing a muffin or chihuahua. Leveraging the M&C dataset's unique region of interest labels, we find that recall is the metric that most strongly correlates the zoom-in region with final task performance. Our model and code for reproduction is publicly available under https://github.com/UKPLab/emnlp2026-zoom-in

Multimodal Large Language Models (MLLMs) require high-resolution visual information to perform fine-grained perception, yet processing entire high-resolution images is computationally prohibitive. While recent methods leverage a Region-of-Interest (RoI) mechanism to focus on salient areas, they typically present a difficult trade-off: training-based approaches depend on large-scale annotated datasets, while training-free methods that utilize the model's internal attention are computationally inefficient and less accurate, requiring either multi-pass prefill stages or reliance on the slow auto-regressive decoding process. In this paper, we propose an efficient, annotation-free Self-Distilled Region Proposal Network (SD-RPN) that resolves this trade-off. The SD-RPN is built around a pipeline that transforms the noisy attention maps from the MLLM's middle layers into high-quality pseudo-RoI labels by explicitly denoising the signal and resolving ambiguity. We use these labels to train a lightweight Region Proposal Network (RPN) that learns a more precise localization. This RPN is also highly efficient, predicting the RoI in a single forward pass using features from the MLLM's middle layers, decoupling RoI identification from the auto-regressive generation and avoiding costly multi-pass operations.To validate our approach, we integrate the framework into the LLaVA-1.5 architecture. Despite being trained on only a few (e.g. 10K) question-answer pairs, our method demonstrates exceptional data efficiency and generalization, achieving over a 10% absolute accuracy improvement on unseen benchmarks, including TextVQA, DocVQA, and V-Star. Our work presents a practical and scalable solution for enhancing the fine-grained perception of MLLMs without requiring costly supervision or full model fine-tuning. Code is available at https://github.com/YuHengsss/SD-RPN.

The paradigm of Multimodal Large Language Models (MLLMs) offers a promising blueprint for advancing the electromagnetic (EM) domain. However, prevailing approaches often deviate from the native MLLM paradigm, instead using task-specific or pipelined architectures that lead to fundamental limitations in model performance and generalization. Fully realizing the MLLM potential in EM domain requires overcoming three main challenges: (1) Data. The scarcity of high-quality datasets with paired EM signals and descriptive text annotations used for MLLMs pre-training; (2) Benchmark. The absence of comprehensive benchmarks to systematically evaluate and compare the performance of models on EM signal-to-text tasks; (3) Model. A critical fragility in low Signal-to-Noise Ratio (SNR) environments, where critical signal features can be obscured, leading to significant performance degradation. To address these challenges, we introduce a tripartite contribution to establish a foundation for MLLMs in the EM domain. First, to overcome data scarcity, we construct and release EM-100k, a large-scale dataset comprising over 100,000 EM signal-text pairs. Second, to enable rigorous and standardized evaluation, we propose EM-Bench, the most comprehensive benchmark featuring diverse downstream tasks spanning from perception to reasoning. Finally, to tackle the core modeling challenge, we present MERLIN, a novel training framework designed not only to align low-level signal representations with high-level semantic text, but also to explicitly enhance model robustness and performance in challenging low-SNR environments. Comprehensive experiments validate our method, showing that MERLIN is state-of-the-art in the EM-Bench and exhibits remarkable robustness in low-SNR settings.

As large language models reshape scientific research, literature retrieval faces a twofold challenge: ensuring source authenticity while maintaining a deep comprehension of academic search intents. While reliable, traditional keyword-centric search fails to capture complex research intents. Frontier LLMs can handle complex research intents, but their high cost and tendency to hallucinate remain key limitations. Here we introduce PaSaMaster, a self-evolving agentic literature retrieval system that produces relevance-scored paper rankings with evidence-grounded recommendations through iterative intent analysis, retrieval, and ranking. It is built on three key designs. First, it transforms literature retrieval from a one shot query--document matching problem into a search process that evolves over time, using ranked evidence to reveal gaps, refine intents, and guide follow-up searches. Second, it prevents hallucinated sources by treating retrieval as intent--paper relevance ranking rather than generation. Finally, PaSaMaster improves cost efficiency by separating planning from retrieval: a frontier LLM is used only for intent understanding, while large scale retrieval and relevance scoring are delegated to customized corpora and lightweight models. Evaluated on the PaSaMaster Benchmark across 38 scientific disciplines, our system exposes the severe inaccuracy and incompleteness of traditional keyword retrieval (improving F1-score by 15.6X) and the unreliability of generative LLMs (which exhibit hallucination rates up to 37.79%). Remarkably, PaSaMaster outperforms GPT-5.2 by 30.0% at a mere 1% of the computational cost while ensuring zero source hallucination: https://github.com/sjtu-sai-agents/PaSaMaster

Multi-modal Large Language Models (MLLMs) are gaining significant attention for their ability to process multi-modal data, providing enhanced contextual understanding of complex problems. MLLMs have demonstrated exceptional capabilities in tasks such as Visual Question Answering (VQA); however, they often struggle with fundamental engineering problems, and there is a scarcity of specialized datasets for training on topics like digital electronics. To address this gap, we propose a benchmark dataset called ElectroVizQA specifically designed to evaluate MLLMs' performance on digital electronic circuit problems commonly found in undergraduate curricula. This dataset, the first of its kind tailored for the VQA task in digital electronics, comprises approximately 626 visual questions, offering a comprehensive overview of digital electronics topics. This paper rigorously assesses the extent to which MLLMs can understand and solve digital electronic circuit questions, providing insights into their capabilities and limitations within this specialized domain. By introducing this benchmark dataset, we aim to motivate further research and development in the application of MLLMs to engineering education, ultimately bridging the performance gap and enhancing the efficacy of these models in technical fields.