text string | source string |
|---|---|
position/orientation between these shots. The movement should be relative to the first image. Note that the objects in the images are assumed to be static. The first image orients X->right, Y->down, Z->forward. Please specify that vector showing exactly how the camera moved in all three dimensions. gpt: Summarily, the ... | https://arxiv.org/abs/2505.17015v1 |
from their initial positions. Remember that movement isn't required. I'm interested in the point-to-point distance of the annotated point in Image-1's shift. gpt: The measured distance of the point's movement is `17` mm.Object Movement-Dot-Distance (ADT) Figure 13. Data samples of object movement-distance. 20 human: Im... | https://arxiv.org/abs/2505.17015v1 |
Deng, Yang Fan, Wenbin Ge, Yu Han, Fei Huang, Binyuan Hui, Luo Ji, Mei Li, Junyang Lin, Runji Lin, Day- iheng Liu, Gao Liu, Chengqiang Lu, Keming Lu, Jianxin Ma, Rui Men, Xingzhang Ren, Xuancheng Ren, Chuanqi Tan, Sinan Tan, Jianhong Tu, Peng Wang, Shijie Wang, Wei Wang, Shengguang Wu, Benfeng Xu, Jin Xu, An Yang, Hao ... | https://arxiv.org/abs/2505.17015v1 |
3, 8 [15] Erfei Cui, Yinan He, Zheng Ma, Zhe Chen, Hao Tian, Weiyun Wang, Kunchang Li, Yi Wang, Wenhai Wang, Xizhou Zhu, Lewei Lu, Tong Lu, Yali Wang, Limin Wang, Yu Qiao, and Jifeng Dai. sharegpt4o. https:// sharegpt4o.github.io/ , 2024. 2 [16] Angela Dai, Angel X Chang, Manolis Savva, Maciej Hal- ber, Thomas Funkhous... | https://arxiv.org/abs/2505.17015v1 |
John Miller, Han- naneh Hajishirzi, Ali Farhadi, and Ludwig Schmidt. Open- clip, 2021. 2 [30] Justin Johnson, Bharath Hariharan, Laurens Van Der Maaten, Li Fei-Fei, C Lawrence Zitnick, and Ross Girshick. Clevr: A diagnostic dataset for compositional language and elementary visual reasoning. In CVPR , 2017. 3 [31] Hanby... | https://arxiv.org/abs/2505.17015v1 |
Liu, Bo Zhang, Bingxuan Wang, Kai Dong, Bo Liu, Jingxiang Sun, Tongzheng Ren, Zhuoshu Li, Hao Yang, et al. Deepseek-vl: towards real-world vision- language understanding. arXiv:2403.05525 , 2024. 2 [47] Pan Lu, Hritik Bansal, Tony Xia, Jiacheng Liu, Chunyuan Li, Hannaneh Hajishirzi, Hao Cheng, Kai-Wei Chang, Michel Gal... | https://arxiv.org/abs/2505.17015v1 |
Yang, Adithya Iyer, Xichen Pan, et al. Cambrian- 1: A fully open, vision-centric exploration of multimodal llms. arXiv preprint arXiv:2406.16860 , 2024. 3 [63] Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth ´ee Lacroix, Baptiste Rozi `ere, Naman Goyal, Eric Hambro, Faisal Azh... | https://arxiv.org/abs/2505.17015v1 |
Delving into RL for Image Generation with CoT: A Study on DPO vs.GRPO Chengzhuo Tong∗4, Ziyu Guo∗1, Renrui Zhang∗†2, Wenyu Shan3, Xinyu Wei3 Zhenghao Xing1, Hongsheng Li2, Pheng-Ann Heng1 CUHK1MiuLar Lab &2MMLab3Peking University4Shanghai AI Lab ∗Equal Contribution†Project Leader Abstract Recent advancements underscore... | https://arxiv.org/abs/2505.17017v1 |
data boosts DPO's in- and out-of-domain performance.Figure 1: Investigation for GRPO and DPO in Autoregressive Image Generation. We analyze the advantages of GRPO and DPO in both in-domain and out-of-domain scenarios (Top-left), the effect of different reward models (Top-right), and the influence of scaling strategies ... | https://arxiv.org/abs/2505.17017v1 |
in handling prompts of varying granularity. In our settings, we leverage preference data derived from a unified reward model, conducting a rigorous comparative analysis. Observation: 1) The off-policy DPO method demonstrates superior performance on in- domain tasks compared to GRPO. 2) Conversely, GRPO exhibits stronge... | https://arxiv.org/abs/2505.17017v1 |
comprehensively evaluating different reward models including HPS [ 54], ImageReward [ 56], Unified Reward [ 51], Fine-tuned ORM [ 18], and ‘Metric Reward’. Reward TypeAverageAttribute Binding Object RelationshipComplex Color Shape Texture Spatial Non-Spatial GRPO DPO GRPO DPO GRPO DPO GRPO DPO GRPO DPO GRPO DPO GRPO DP... | https://arxiv.org/abs/2505.17017v1 |
substantial breakthroughs in lifting the reasoning capabilities of LLMs via Chain-of-Thought (CoT) techniques [ 52,35,11,45, 2,1]. Existing researches indicate that GRPO, the on-policy RL algorithm, can data-efficiently enhance performance on in-domain (ID) tasks without sacrificing capabilities on out-of-domain (OOD) ... | https://arxiv.org/abs/2505.17017v1 |
in Table 1 and 2, we evaluate the in-domain and out-of-domain performance of GRPO and DPO. We provide qualitative results in Figure 2, with additional visualization in the Supplementary. The key findings are summarized as follows: •DPO demonstrates stronger performance than GRPO in in-domain evaluations. As shown in Ta... | https://arxiv.org/abs/2505.17017v1 |
human-annotated image rankings, these models provide a holistic assessment of visual quality, generating scores that reflect human-like preferences. •Visual Question Answering Model. Visual Question Answering Models, including Uni- fiedReward [ 51], Fine-tuned ORM [ 18] and PARM [ 18], leverage multimodal large languag... | https://arxiv.org/abs/2505.17017v1 |
perfectly with our prior evaluations of the intrinsic generalization capabilities of these models. This indicates that the reward model’s intrinsic capacity for generalization is a pivotal factor that probably contributes to the overall generalization potential of the RL algorithm. 2.4 Investigation of Effective Scalin... | https://arxiv.org/abs/2505.17017v1 |
GRPO DPO Baseline 78.04 63.50 54.37 76.25 98.44 87.63 88.03 Data Scaling Base Size 79.18 77.31 63.00 70.25 60.62 48.12 78.75 67.25 86.87 90.15 99.69 98.75 86.17 89.63 Double Size 80.28 78.88 66.50 67.50 62.81 50.31 78.25 77.00 87.88 91.67 98.75 99.06 87.50 87.88 Triple Size 78.21 79.25 64.50 70.00 56.56 51.25 73.75 76.... | https://arxiv.org/abs/2505.17017v1 |
The sharp, angular lines of the skyscrapers jutted up into the sky, a towering testament to human ingenuity and ambition.A photo of a green teddy bear and a brown kite.BaseIter1Iter2Iter3BaseIter1Iter2Iter3 BaseSample 8Sample 12Sample 16BaseSample 8Sample 12Sample 16 Base SizeDouble SizeTriple SizeBase SizeDouble SizeT... | https://arxiv.org/abs/2505.17017v1 |
estimation with larger group sizes, which stabilizes policy updates and strengthens in-domain optimization. Given that doubling each factor (group size, in-domain data scale, or iterative training paradigms) incurs approximately comparable computational cost, prioritizing scaling sampling emerges as a highly efficient ... | https://arxiv.org/abs/2505.17017v1 |
C: Detailed record of computational time. A Related Work Visual Generative Models. Visual generative models have advanced through two primary paradigms: autoregressive and diffusion approaches. Autoregressive methods, inspired by lan- guage modeling success [ 33,34,47,59], sequentially predict image tokens or pixels, a... | https://arxiv.org/abs/2505.17017v1 |
similar). Allowed color descriptors: basic colors (e.g., red, blue, green, yellow, pink, purple, orange, brown, black, white, gray) and common material-based variations (e.g., "golden", "silver", "ivory"). Avoid uncommon or overly specific colors (e.g., "cerulean", "chartreuse"). Object Selection: The first object shou... | https://arxiv.org/abs/2505.17017v1 |
2025. [3]Arash Ahmadian, Chris Cremer, Matthias Gallé, Marzieh Fadaee, Julia Kreutzer, Olivier Pietquin, Ahmet Üstün, and Sara Hooker. Back to basics: Revisiting reinforce style optimization for learning from human feedback in llms. arXiv preprint arXiv:2402.14740 , 2024. [4]Aida Amini, Saadia Gabriel, Peter Lin, Rik K... | https://arxiv.org/abs/2505.17017v1 |
Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, et al. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:2501.12948 , 2025. [17] Ziyu Guo, Ray Zhang, Hao Chen, Jialin Gao, Dongzhi Jiang, Jiaze W... | https://arxiv.org/abs/2505.17017v1 |
https://chat.openai.com , 2023. [34] OpenAI. Hello gpt-4o. https://openai.com/index/hello-gpt-4o/ , 2024. [35] OpenAI, Aaron Jaech, Adam Kalai, Adam Lerer, et al. OpenAI o1 system card, 2024. [36] Long Ouyang, Jeff Wu, Xu Jiang, Diogo Almeida, Carroll L. Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katari... | https://arxiv.org/abs/2505.17017v1 |
Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. Self-consistency improves chain of thought reasoning in language models. In International Conference on Learning Representations (ICLR) , 2023. [51] Yibin Wang, Yuhang Zang, Hao Li, Cheng Jin, and Jiaqi Wang. Unified reward model for multimodal understanding and gener... | https://arxiv.org/abs/2505.17017v1 |
Ziniu Hu, Yisong Yue, Yuxiao Dong, and Jie Tang. ReST-MCTS*: Llm self-training via process reward guided tree search. Advances in Neural Information Processing Systems , 37:64735–64772, 2024. [63] Lvmin Zhang, Anyi Rao, and Maneesh Agrawala. Adding conditional control to text-to-image diffusion models. In Proceedings o... | https://arxiv.org/abs/2505.17017v1 |
arXiv:2505.17022v1 [cs.CV] 22 May 2025GoT-R1: Unleashing Reasoning Capability of MLLM for Visual Generation with Reinforcement Learning Chengqi Duan1∗, Rongyao Fang2∗, Yuqing Wang1∗, Kun Wang3, Linjiang Huang4, Xingyu Zeng3,Hongsheng Li2,Xihui Liu1‡ 1HKU MMLab,2CUHK MMLab,3Sensetime,4Beihang University Abstract Visual ... | https://arxiv.org/abs/2505.17022v1 |
meticulously crafted, vintage-style topper featuring a butterfly (240,38),(548,317) made entirely of sugar paste. The butterfly's wings are delicately detailed, showcasing a gradient of warm oranges and yellows, adorned with intricate patterns and sparkling accents that catch the light. Prompt:A butterfly on the left o... | https://arxiv.org/abs/2505.17022v1 |
MLLMs’ spatial evaluation capability by transforming bounding box coordinates into visualized bounding boxes drawn on a blank canvas, improving the reliability of the prompt-to-reasoning spatial reward. Through careful reward design and the adoption of Group Relative Policy Optimization (GRPO) [ 7], GoT-R1 enables mode... | https://arxiv.org/abs/2505.17022v1 |
Policy Optimization (GRPO) [ 38]. GRPO is an efficient reinforcement learning technique that enhances policy learning by evaluating and normalizing rewards among a group of sampled candidate outputs from the model, eliminating the need for a separate critic model. Recent work has extended these techniques to multimodal... | https://arxiv.org/abs/2505.17022v1 |
diverse scenarios. Moreover, the GoT framework trained with supervised fine-tuning tends to generate templated but sometimes infaithful reasoning chains, which can bottleneck subsequent visual generation. Group Relative Policy Optimization (GRPO) Group Relative Policy Optimization (GRPO) is proposed by DeepSeek-R1 [ 38... | https://arxiv.org/abs/2505.17022v1 |
assesses both reasoning quality and generation fidelity. The model parameters are updated using GRPO to encourage high-reward reasoning strategies and generated images, and discourage the low-reward ones. The specific design of our reward function, which addresses the unique challenges of evaluating visual reasoning qu... | https://arxiv.org/abs/2505.17022v1 |
and properly formatted? Prompt:A bee next to a microwaveGoT(spatial):bee:(501,174),(930,752) microwave:(0,204),(434,793) MLLMRewardModel GoTSpatialReward Figure 4: Prompt-Reasoning Spatial Reward Rspa process. For robust spatial evaluation, the MLLM assesses bounding boxes rendered on an image from the GoT’s textual co... | https://arxiv.org/abs/2505.17022v1 |
denote further training via GRPO on the GoT-finetuned checkpoints. GoT-R1 models are evaluated under guidance scale 5. JourneyDB-GoT [ 39] and FLUX-GoT [ 10] datasets for 70000 steps, followed by 1000 steps of GRPO. Our constructed dataset for GRPO consists of prompts from T2I-Compbench [ 21] training dataset and Laion... | https://arxiv.org/abs/2505.17022v1 |
our GRPO-enhanced model GoT-R1-7B. Our model demonstrates superior performance on prompt alignment and image quality. Method Rsem Rspa RRI RPI Color Shape Texture 2D-Spatial Non-Spatial Complex Baseline × × × × 0.6336 0.4456 0.5621 0.2140 0.3070 0.3490 wRPR ✓ ✓ × × 0.7050 0.4671 0.6075 0.2283 0.3089 0.3619 wRRI × ×✓ × ... | https://arxiv.org/abs/2505.17022v1 |
rewarding the final generated image. Furthermore, using only RRI can be detrimental, because the absence of prompt-reasoning reward RPRresults in a misaligned reasoning process and thus provides harmful guidance to image generation. Further experiments in Table 2, where individual reward components are removed from our... | https://arxiv.org/abs/2505.17022v1 |
as misuse for disinformation, and to ensure ethical application. References [1]Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 , 2023. [2]Jinze Bai... | https://arxiv.org/abs/2505.17022v1 |
object-focused framework for evaluating text-to-image alignment. Advances in Neural Information Processing Systems , 36:52132–52152, 2023. [17] Jian Han, Jinlai Liu, Yi Jiang, Bin Yan, Yuqi Zhang, Zehuan Yuan, Bingyue Peng, and Xiaobing Liu. Infinity: Scaling bitwise autoregressive modeling for high-resolution image sy... | https://arxiv.org/abs/2505.17022v1 |
Prafulla Dhariwal, Alex Nichol, Casey Chu, and Mark Chen. Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125 , 1(2):3, 2022. [35] Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, and Björn Ommer. High-resolution image synthesis with latent diffusion models.... | https://arxiv.org/abs/2505.17022v1 |
Liu, Zhenda Xie, Xingkai Yu, Chong Ruan, et al. Janus: Decoupling visual encoding for unified multimodal understanding and generation, 2024a. URL https://arxiv. org/abs/2410.13848 , 2024. [50] Xiaoshi Wu, Yiming Hao, Keqiang Sun, Yixiong Chen, Feng Zhu, Rui Zhao, and Hongsheng Li. Human preference score v2: A solid ben... | https://arxiv.org/abs/2505.17022v1 |
LlamaGen [40] Autoregressive 0.32 0.71 0.34 0.21 0.58 0.07 0.04 Chameleon [42] Autoregressive 0.39 - - - - - - LWM [25] Autoregressive 0.47 0.93 0.41 0.46 0.79 0.09 0.15 SEED-X [15] Unet+Llama 0.49 0.97 0.58 0.26 0.80 0.19 0.14 Emu3-Gen [45] Autoregressive 0.54 0.98 0.71 0.34 0.81 0.17 0.21 Janus [49] Autoregressive 0.... | https://arxiv.org/abs/2505.17022v1 |
inconsistencies or additions that don’t contradict the prompt - 9-10: Perfect alignment. The detailed caption faithfully includes all elements from the brief prompt with appropriate elaboration Brief prompt: <Prompt> Detailed caption: <Reasoning Chain> Note to only ouput with a dictionary with score in this format: {"s... | https://arxiv.org/abs/2505.17022v1 |
including the spatial relationship observed", "caption": repeat of the image caption provided, "reasoning": "ONE sentence explaining if the spatial positioning in the image EXACTLY matches or contradicts the caption", "score": ... }} Output only the python dictionary with nothing else. <Image> Generated Image </Image> ... | https://arxiv.org/abs/2505.17022v1 |
Segerer - Cultural Value Alignment in LLM 1 Cultural Value Alignment in Large Language Models: A Prompt-based Analysis of Schwartz Values in Gemini, ChatGPT, and DeepSeek Author: Robin Segerer; University of Basel/University of Zurich Abstract This study examines cultural value alignment in large language models (LLMs)... | https://arxiv.org/abs/2505.17112v1 |
to treat all values equally, or are some values systematically prioritized? If so, can this prioritization be explained culturally? If LLMs trained predominantly on Western data tend to reflect Western value hierarchies, does the same pattern hold for models developed in non-Western contexts? In other words, could it b... | https://arxiv.org/abs/2505.17112v1 |
al., 1994). Such distinctions are neither absolute nor static, yet they serve as analytical frameworks for understanding cross-cultural variability in ethical reasoning and social organization. Gabriel and Ghazavi (2022)argue that AI should not be aligned with a singular moral framework but should instead be designed t... | https://arxiv.org/abs/2505.17112v1 |
methodologies, and cultural influences (see Dai et al., preprint; Rane et al., 2024): 1. Google Gemini 2.0 – Developed by DeepMind, Gemini integrates multimodal capabilities (text, image, and video analysis) and is trained on diverse, predominantly English-language datasets. It represents a state-of-the-art approach to... | https://arxiv.org/abs/2505.17112v1 |
Tradition: Respecting and preserving cultural and religious heritage. Example item: "Religious belief is important to him. He tries hard to do what his religion requires." 3. Self-Transcendence – Concerned with the well-being of others and universal moral principles: o Benevolence: Prioritizing close social relationshi... | https://arxiv.org/abs/2505.17112v1 |
ratings in most categories. The largest difference between models was observed in the Self-enhancement and Openness dimensions, where DeepSeek's ratings were substantially lower than those of Gemini and ChatGPT. In contrast, ratings for the Conservative dimension were more similar across models. To further assess these... | https://arxiv.org/abs/2505.17112v1 |
an agent that seeks power or personal advancement (e.g., DeepSeek: “As an AI, I don’t have personal goals, ambitions, or the desire to impress others. My purpose is to assist and provide value to users, not to seek success or recognition for myself. I operate based on functionality and user needs, not personal aspirati... | https://arxiv.org/abs/2505.17112v1 |
to identify recurring biases and refine ethical justifications through reinforcement learning. A medical triage AI, for example, could track prior decisions to ensure it does not favor specific demographics, adjusting its reasoning when inconsistencies arise. (3) Dynamic value contextualization. Furthermore, AI should ... | https://arxiv.org/abs/2505.17112v1 |
N., Choudhary, S., & Rane, J. (2024). Gemini Versus ChatGPT: Applications, Performance, Architecture, Capabilities, and Implementation. SSRN Electronic Journal. https://doi.org/10.2139/ssrn.4723687 Rodriguez-Soto, M., Serramia, M., Lopez-Sanchez, M., & Rodriguez-Aguilar, J. A. (2022). Instilling moral value alignment b... | https://arxiv.org/abs/2505.17112v1 |
arXiv:2505.17114v1 [cs.CL] 21 May 2025 RAVEN: Query-Guided R epresentation Alignment for Question Answering over A udio, V ideo, E mbedded Sensors, and N atural Language Subrata Biswas, Mohammad Nur Hossain Khan, Bashima Islam Department of Electrical & Computer Engineering Worcester Polytechnic Institute Worcester, MA... | https://arxiv.org/abs/2505.17114v1 |
perception- language reasoning by combining pretrained LLMs with modality-specific encoders and fusion strate- gies (Liu et al., 2023a; Lin et al., 2023a; Chu et al., 2023). Models such as Flamingo (Awadalla et al., 2023), Video-LLaMA (Zhang et al., 2023a), and A Vicuna (Tang et al., 2024) have achieved strong results ... | https://arxiv.org/abs/2505.17114v1 |
✓ ✗Egocentric videoOE LLMs 1.2K MM-Ego ✓ ✓ ✗Multimodal (A V)OE / MCAccuracy, LLMs /CE10K A VS-QA ✓ ✓ ✓Egocentric videoMC / OE TF /CELLMs 300K prior systems-demonstrating robust, query-aware reasoning across diverse multimodal inputs. We summarize our contributions below: •We propose RAVEN , a unified QA model that inte... | https://arxiv.org/abs/2505.17114v1 |
proposed QuART as- signs query-conditioned scalar weights to cross- modal tokens, enabling selective fusion and robust reasoning under disagreement. Multi-modal Datasets . Existing corpora sup- port audio-visual (e.g., HowTo100M (Chen et al., 2024b), AudioCaps (Kim et al., 2019)) and image- language learning (e.g., CC3... | https://arxiv.org/abs/2505.17114v1 |
. For each candidate pair, the Critic applies an ensemble of instruction-tuned LLMs to assess QA quality. Inspired by LLM-as-judge paradigms (Fu et al., 2023; Zheng et al., 2023a), we define a quality vec- torC(q, A) = [s1, s2, s3, s4, s5]∈R5, where each score corresponds to one of five axes: answerabil- ity,hallucinat... | https://arxiv.org/abs/2505.17114v1 |
Encover A Projector A Encoder Query To Token AlignmentModuleLLM QueryPerturbationModuleFigure 3: Overview of RAVEN . Each modality (video, audio, sensor) is encoded using pretrained encoders and projected into a shared space. The QuART module performs query-conditioned token relevance scoring to align informative token... | https://arxiv.org/abs/2505.17114v1 |
paired with raw modality inputs, such as video subtitles, au- dio narrations, and wearable sensor logs. For each modality m∈ {v, a, s}, we freeze the pretrained encoder Φm(·)and language model Π, and update only the corresponding projection head Pmto align with textual supervision. All three branches are trained in suc... | https://arxiv.org/abs/2505.17114v1 |
2024), and Video-LLaMA2 (Cheng et al., 2024b); for exocen- tric QA: OpenFlamingo (Awadalla et al., 2023), BLIP-2.6 (Li et al., 2023b), VideoChat-7B (Li et al., 2023c), LLaV A-1.5 (Liu et al., 2024a), MiniGPT4 (Zhu et al., 2023b), InstructBLIP (Liu et al., 2023b), LLaMA-Adapter (Zhang et al., 2023b), VideoLLaV A (Lin et... | https://arxiv.org/abs/2505.17114v1 |
(0.51–0.54). These gains stem from QuART ’s query-to-token alignment, which emphasizes semantically relevant tokens even un- der modality misalignment. 6.2 Ablation Study Training Stages and Loss Conditioning . We ab- late training stages, loss formulation, and regular- ization strength across six QA benchmarks (Ta- bl... | https://arxiv.org/abs/2505.17114v1 |
0.17 A V-LLM 24.7 22.1 49.8 26.8 - - - - Video-LLaMA 17.9 24.6 31.5 25.3 0.28 0.39 0.33 0.33 A Vicuna 34.1 31.3 51.7 31.9 - - - - Video-LLaMA2 43.2 44.7 52.1 29.7 0.51 0.54 0.48 0.51 RAVEN I, II 51.9 63.7 66.4 52.6 0.69 0.71 0.64 0.68 RAVEN I – III 54.9 69.2 72.8 57.2 0.76 0.79 0.71 0.75 Table 6: Ablation on training s... | https://arxiv.org/abs/2505.17114v1 |
required approximately 120 hours on 4 NVIDIA A100 GPUs (each with 80 GB of memory). While the design is efficient at inference time due to early token filtering, future work could further reduce training cost through distillation or parameter sharing across modalities. Future Directions . Future work on RAVEN in- clude... | https://arxiv.org/abs/2505.17114v1 |
training large autoregressive vision- language models. arXiv preprint arXiv:2308.01390 . Shehreen Azad, Vibhav Vineet, and Yogesh Singh Rawat. 2025. Hierarq: Task-aware hierarchical q- former for enhanced video understanding. arXiv preprint arXiv:2503.08585 . Jinze Bai, Shuai Bai, Yunfei Chu, Zeyu Cui, Kai Dang, Xiaodo... | https://arxiv.org/abs/2505.17114v1 |
Zhou, Qian Yang, Shil- iang Zhang, Zhijie Yan, Chang Zhou, and Jingren Zhou. 2023. Qwen-audio: Advancing universal audio understanding via unified large-scale audio- language models. arXiv preprint arXiv:2311.07919 . Justin Cosentino, Anastasiya Belyaeva, Xin Liu, Nicholas A Furlotte, Zhun Yang, Chace Lee, Erik Schenck... | https://arxiv.org/abs/2505.17114v1 |
language model with few- shot learning and dialogue abilities. arXiv preprint arXiv:2402.01831 . Alexandre Lacoste, Sasha Luccioni, Victor Schmidt, and Thomas Dandres. 2019. Quantifying the car- bon emissions of machine learning. arXiv preprint arXiv:1910.09700 . Zikang Leng, Amitrajit Bhattacharjee, Hrudhai Ra- jasekh... | https://arxiv.org/abs/2505.17114v1 |
detailed video understanding via large vision and language models. arXiv preprint arXiv:2306.05424 . Mohammad Malekzadeh, Richard G Clegg, Andrea Cavallaro, and Hamed Haddadi. 2019. Mobile sensor data anonymization. In Proceedings of the interna- tional conference on internet of things design and implementation , pages... | https://arxiv.org/abs/2505.17114v1 |
Thor Siiger Prentow, Mikkel Baun Kjærgaard, Anind Dey, Tobias Sonne, and Mads Møller Jensen. 2015. Smart devices are different: Assessing and mitigat- ingmobile sensing heterogeneities for activity recog- nition. In Proceedings of the 13th ACM conference on embedded networked sensor systems , pages 127– 140. Yixuan Su,... | https://arxiv.org/abs/2505.17114v1 |
and Ubiquitous Technologies , 8(1):1–32. An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, and 1 others. 2024. Qwen2. 5 technical report. arXiv preprint arXiv:2412.15115 . Pinci Yang, Xin Wang, Xuguang Duan, Hong Chen, Runze Hou, Cong Jin, and Wenw... | https://arxiv.org/abs/2505.17114v1 |
pretraining to n-modality by language-based semantic alignment. arXiv preprint arXiv:2310.01852 . Deyao Zhu, Jun Chen, Xiaoqian Shen, Xiang Li, and Mohamed Elhoseiny. 2023b. Minigpt-4: Enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 . xiv A More Related Works... | https://arxiv.org/abs/2505.17114v1 |
beyond 25 words. These distributions high- light the reasoning and generation challenges posed byA VS-QA . License .A VS-QA is released under a CC-BY 4.0 license, along with the full generation pipeline, in- cluding prompts, templates, and filtering scripts. B.2 Quality Ranking via LLM Scoring To evaluate the quality o... | https://arxiv.org/abs/2505.17114v1 |
and au- tomatic judgments. This suggests that our LLM- based scoring framework is a reliable proxy for human evaluation at scale. We recruited two annotators through internal advertisements at the host institution. Both male annotators were between 25–35 years old and had a basic understanding of large language models.... | https://arxiv.org/abs/2505.17114v1 |
grounding, and language consis- tency. The human prompt (Figure 10) ensures no hallucinated corrections are introduced—only local improvements to existing QA pairs. In the Critic phase, large language models are prompted to rate the quality of each generated question–answer pair using four dimensions: rel- evance, corr... | https://arxiv.org/abs/2505.17114v1 |
KEY IMPROVEMENTS IN THE OUTPUT OR ANY OTHER TEXT EXCEPT QUESTIONS AND ANSWERS. Figure 10: User prompt used for generating questions and answers in Evaluator phase. numerical evaluations across samples. Each QA pair receives two scores (one for the question, one for the answer), which are then aggregated across multiple... | https://arxiv.org/abs/2505.17114v1 |
and spatial reasoning over egocentric and exocentric scenes. The code is released under the Apache 2.0 license and used strictly for research purposes. C.3 Projection Layer Each modality-specific encoder output is projected to the LLM input dimension using a tailored strat- egy. The output of the audio encoder is proje... | https://arxiv.org/abs/2505.17114v1 |
data ( A VS-QA ), we use publicly available datasets to train the video, au- dio, and sensor encoders. To pre-train the sensorencoder, we use epic kitchen (Damen et al., 2018), ego4D (Grauman et al., 2022),HHAR (Stisen et al., 2015), UCI-HAR (Reyes-Ortiz et al., 2016), Shoaib (Shoaib et al., 2014), Motion- Sense (Malek... | https://arxiv.org/abs/2505.17114v1 |
input space. It is trained via instruction tuning and multi-modal supervised learning, enabling videocaptioning, question answering, and reasoning with generalization from few-shot examples. Video-LLaMA2 . Video-LLaMA-2 builds upon its predecessor by introducing spatio-temporal con- nectors, which better align video re... | https://arxiv.org/abs/2505.17114v1 |
Vicuna. It uses Q-Former modules to encode BEATs for audio and CLIP for video features, and feeds these to the LLM via a learned query-token bridge. OpenFlamingo . OpenFlamingo fuses a frozen CLIP-ViT with a pre-trained language model via a perceiver-style cross-attention module. The key innovation lies in its interlea... | https://arxiv.org/abs/2505.17114v1 |
image-text dataset containing approximately 3 million image- caption pairs sourced from the web. The captions are filtered and cleaned alt-text annotations that loosely describe the visual content. While the de- scriptions can be noisy and lack fine-grained de- tail, it is valuable for large-scale vision-language pretr... | https://arxiv.org/abs/2505.17114v1 |
are crafted to assess fine-grained audio- visual reasoning, where answers depend on spatial, temporal, and semantic alignment of what is seen and heard. A VQA . A VQA is a benchmark dataset specifically designed for evaluating audio-visual reasoning ca- pabilities in multimodal models. It includes videos paired with op... | https://arxiv.org/abs/2505.17114v1 |
tasks. Datasets Audio EncoderMSVD- QAMSRVTT- QAActivityNet- QA Whisper-T 66.5 51.6 46.2 Whisper-B 67.7 53.1 47.4 Whisper-S 68.1 53.9 47.6 BEATs 73.3 63.1 57.6 LoRA rank Accuracy (%) 020406080 0 100 200 300AVSD MUSIC-QA AVSSD MSVD-QA ActivityNet-QA Figure 14: Impact of LoRA rank on QA accuracy across five benchmarks. Ac... | https://arxiv.org/abs/2505.17114v1 |
inclusion of sensor data consistently improves robustness and interpretability. In particular, 17 and 18 highlight how sensor in- formation enhances the correctness and relevance of both the predicted answer and its supporting ex- planation. Conversely, Figure 19 presents a failure case where the model, even with full ... | https://arxiv.org/abs/2505.17114v1 |
suggest movement of the arm to reach for the soap . Figure 17: Example demonstrating the added value of sensor data in identifying subtle concurrent actions. Given the question “Is the person engaged in any other activities other than washing hands?” , the Audio+Video model detects only hand presence and water sounds, ... | https://arxiv.org/abs/2505.17114v1 |
arXiv:2505.17116v1 [cs.CL] 21 May 2025Comparative Evaluation of Prompting and Fine-Tuning for Applying Large Language Models to Grid-Structured Geospatial Data Akash Dhruv1Yangxinyu Xie1 2Jordan Branham3Tanwi Mallick1 Abstract This paper presents a comparative study of large language models (LLMs) in interpreting grid-... | https://arxiv.org/abs/2505.17116v1 |
support urban plan- ning and hazard adaptation across the United States, into agentic LLM workflows for deployment in GPT-like chat interfaces. ClimRR provides projections of extreme tem- perature, precipitation, wind speed, humidity, and fire weather indices under two Representative Concentration Pathways (RCP 4.5 and... | https://arxiv.org/abs/2505.17116v1 |
both RCP 4.5 and RCP 8.5 emissions scenar- ios, along with regional aggregates; (4) A ground-truth re- sponse combining precise value extraction with natural lan- guage interpretation. This dataset was generated via a semi-automated pipeline that queries the original ClimRR data source, extracts relevant variables for ... | https://arxiv.org/abs/2505.17116v1 |
Each prompt consisted of two components: • A structured input block containing grid-indexed data for a single cell, including historical values, projec- tions under RCP 4.5 and RCP 8.5 scenarios, and fluc- tuations relative to the region (state, county, etc.) ag- gregate. • A natural language user query requesting spec... | https://arxiv.org/abs/2505.17116v1 |
isons. In contrast, fine-tuned models show improved alignment with reference answers across all categories, demonstrating an enhanced understanding of domain-specific nuances. & Biases (wandb)3for reproducibility. The resulting fine- tuned model exhibited improved spatial reasoning and ro- bustness in producing value-a... | https://arxiv.org/abs/2505.17116v1 |
re- search in accordance with the DOE Public Access Plan. http://energy.gov/downloads/doe-public-access-plan. References Daniel Han, M. H. and team, U. Unsloth, 2023. URL http://github.com/unslothai/unsloth . Dettmers, T., Lewis, M., Shleifer, S., and Zettlemoyer, L. 8-bit optimizers via block-wise quantization, 2022. ... | https://arxiv.org/abs/2505.17116v1 |
5 Comparative Evaluation of Prompting and Fine-Tuning for Applying LLMs to Grid-Structured Geospatial Data Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., Lacroix, T., Rozi `ere, B., Goyal, N., Hambro, E., Azhar, F., Rodriguez, A., Joulin, A., Grave, E., and Lam- ple, G. Llama: Open and efficient fo... | https://arxiv.org/abs/2505.17116v1 |
From Tokens to Thoughts: How LLMs and Humans Trade Compression for Meaning Chen Shani Stanford University cshani@stanford.eduDan Jurafsky Stanford University jurafsky@stanford.edu Yann LeCun New York University, Meta - FAIRRavid Shwartz-Ziv New York University, Wand.AI Abstract Humans organize knowledge into compact ca... | https://arxiv.org/abs/2505.17117v2 |
preservation of semantic meaning . Do LLMs develop conceptual structures mirroring the efficiency and richness of human thought, or do they employ fundamentally different representational strategies? To address this, we introduce a novel quantitative methodology rooted in information theory. We develop and apply a fram... | https://arxiv.org/abs/2505.17117v2 |
when forming concepts? These three questions steer our investigation, which approaches each through the unifying lens of the information-theoretic framework detailed in Section 4. RQ1 begins by examining the alignment of broad conceptual categories, a key aspect of how information is compressed. RQ2 then delves into th... | https://arxiv.org/abs/2505.17117v2 |
conceptual representation might vary with compu- tational architecture and scale. This selection covers prevalent architectural paradigms (encoder-only, decoder-only) and a wide spectrum of model sizes, from 300 million to 72 billion parameters. Our analysis features encoder-only models from the BERT family (e.g., BERT... | https://arxiv.org/abs/2505.17117v2 |
RQ3 employs a unified objective function, L(detailed below), to quantitatively assess the total efficiency with which LLMs and human systems navigate this fundamental trade-off. The following subsections detail the theoretical underpinnings of this framework. 4.1 Theoretical Underpinnings: Rate-Distortion Theory and th... | https://arxiv.org/abs/2505.17117v2 |
This assumes that for this complexity calculation, items within each cluster Cc(of size |Cc|) are indistinguishable beyond their shared label c. Thus: Complexity (X, C ) = log2|X| −1 |X|X c∈C|Cc|log2|Cc|. (2) This term formalizes the representational compactness aspect central to [RQ1]. The Distortion Term: The second ... | https://arxiv.org/abs/2505.17117v2 |
of its human- assigned category name (e.g., ‘robin‘ to ‘bird‘). These LLM-derived similarities are then correlated (Spearman’s ρ) with human typicality ratings from our cognitive science datasets. [RQ3] Evaluating the Efficiency of the Compression-Meaning Trade-off To evaluate the overall balance of compression and mea... | https://arxiv.org/abs/2505.17117v2 |
we calculated the cosine similarity between each item’s token embedding and the token embedding of its *human-assigned category name* (e.g., ‘robin‘ vs. ‘bird‘). These item-to-category-label similarities were then correlated (Spearman’s ρ[Wissler, 1905]) with human-rated typicality scores. Results and Observations : Sp... | https://arxiv.org/abs/2505.17117v2 |
a more statistically “optimal” trade-off between minimizing complexity and distortion within our framework, this implies LLMs are more “efficient” by this specific information-theoretic benchmark. Interpretation : The combined results from entropy and the Lobjective strongly indicate a fundamen- tal difference in repre... | https://arxiv.org/abs/2505.17117v2 |
to abstract human-like conceptual information. This observation highlights important avenues for future AI development focused on enhancing human-AI alignment. These divergent representational strategies carry significant implications. For AI development , achieving more human-like understanding demands moving beyond c... | https://arxiv.org/abs/2505.17117v2 |
herd of models. arXiv preprint arXiv:2407.21783 , 2024. Pengcheng He, Xiaodong Liu, Jianfeng Gao, and Weizhu Chen. Deberta: Decoding-enhanced bert with disentangled attention. arXiv preprint arXiv:2006.03654 , 2020. Nhat Hoang-Xuan, Minh Vu, and My T Thai. Llm-assisted concept discovery: Automatically identifying and e... | https://arxiv.org/abs/2505.17117v2 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.