Daily Papers

We study timestamped speaker-attributed automatic speech recognition (SA-ASR) for long-form, multi-party speech with overlap. In this setting, chunk-wise inference must preserve meeting-level speaker identity consistency while producing time-stamped, speaker-labeled transcripts. Prior Speech-LLM systems tend to prioritize either local diarization or global labeling, lacking the ability to jointly model fine-grained temporal boundaries and robust cross-chunk identity linking. We propose G-STAR, an end-to-end framework that couples a cache-conditioned speaker-tracking module with a Speech-LLM transcription backbone. The tracker provides structured speaker cues with temporal grounding, and the LLM generates attributed text conditioned on these cues. G-STAR supports component-wise optimization and joint end-to-end training, enabling flexible learning under heterogeneous supervision and domain shift. Under chunk-wise decoding protocols, experiments on both oracle-segmented local evaluation and full-meeting global evaluation show strong speaker-attributed transcription performance.

Recent breakthroughs in video diffusion models have significantly accelerated the development of video editing techniques. However, existing methods often rely on inpainting video frames based on masked input, which requires extracting the target video mask in advance, and the precision of the segmentation directly affects the quality of the completion. In this paper, we present SEDiT, a novel one-stage video Subtitle Erasure approach via One-step Diffusion Transformer. We introduce a mask-free inference approach that enables direct erasure of the targeted subtitle. The proposed one-stage framework mitigates the sub-optimality inherent in the two-stage processing of prior models. Since subtitle removal is a localized editing task in which most pixels remain unchanged, the underlying distribution shift is minimal, making it well-suited to one-step generation under rectified flow. We empirically validate the reliability of one-step denoising and further provide a formal theoretical justification. Under the localized-editing structure of subtitle removal, the conditional optimal transport (OT) map and its induced rectified flow velocity field are Lipschitz continuous with respect to the latent variable, which underpins the theoretical feasibility of one-step sampling. To address the challenge of long-term temporal consistency, we adopt a hybrid training strategy by occasionally conditioning the model with a clean first-frame latent. This facilitates temporal continuity, allowing each segment during inference to leverage the output of its predecessor. To avoid visible seams caused by cropping and reinserting processed targets, particularly in scenarios involving substantial motion, we feed the original video directly into SEDiT. Thanks to one-step and chunk-wise streaming inference, our method can efficiently handle native 1440p video with infinite length.

While long-context large language models (LLMs) exhibit remarkable document processing capabilities, their prohibitively high training costs often hinder customized applications. To mitigate this issue, we propose Sequential Chunk-wise Optimization (SeCO), a memory-efficient training paradigm that partitions lengthy inputs into manageable chunks. Each chunk independently constructs its computational graph and performs localized backpropagation, ensuring that only one chunk's forward activations are stored in memory. Building on SeCO, we further introduce Sparse Chunk-wise Optimization (SpaCO), which reduces computational overhead by selectively propagating gradients to specific chunks and incorporates a carefully designed compensation factor to ensure unbiased gradient estimation. SpaCO decouples the computational cost of backpropagation from the context length, enabling training time to gradually converge to inference time as sequences become longer. Implemented as lightweight training wrappers, both SeCO and SpaCO offer substantial practical benefits. For example, when fine-tuning an 8B model with LoRA on a single RTX 3090 GPU, SeCO expands maximum sequence length from 1K to 16K tokens, while SpaCO demonstrates accelerated training speed -- achieving up to 3x faster than SeCO under the same experimental setup. These innovations provide new insights into optimizing long-context models, making them more accessible for practical applications. We have open-sourced the code at https://github.com/wenhaoli-xmu/seco{here}.

Linearizing pretrained large language models (LLMs) primarily relies on intra-layer hybrid attention mechanisms to alleviate the quadratic complexity of standard softmax attention. Existing methods perform token routing based on sliding-window partitions, resulting in position-based selection and fails to capture token-specific global importance. Meanwhile, linear attention further suffers from distribution shift caused by learnable feature maps that distort pretrained feature magnitudes. Motivated by these limitations, we propose STILL, an intra-layer hybrid linearization framework for efficiently linearizing LLMs. STILL introduces a Self-Saliency Score with strong local-global consistency, enabling accurate token selection using sliding-window computation, and retains salient tokens for sparse softmax attention while summarizing the remaining context via linear attention. To preserve pretrained representations, we design a Norm-Preserved Feature Map (NP-Map) that decouples feature direction from magnitude and reinjects pretrained norms. We further adopt a unified training-inference architecture with chunk-wise parallelization and delayed selection to improve hardware efficiency. Experiments show that STILL matches or surpasses the original pretrained model on commonsense and general reasoning tasks, and achieves up to a 86.2% relative improvement over prior linearized attention methods on long-context benchmarks.

We present MAGI-1, a world model that generates videos by autoregressively predicting a sequence of video chunks, defined as fixed-length segments of consecutive frames. Trained to denoise per-chunk noise that increases monotonically over time, MAGI-1 enables causal temporal modeling and naturally supports streaming generation. It achieves strong performance on image-to-video (I2V) tasks conditioned on text instructions, providing high temporal consistency and scalability, which are made possible by several algorithmic innovations and a dedicated infrastructure stack. MAGI-1 facilitates controllable generation via chunk-wise prompting and supports real-time, memory-efficient deployment by maintaining constant peak inference cost, regardless of video length. The largest variant of MAGI-1 comprises 24 billion parameters and supports context lengths of up to 4 million tokens, demonstrating the scalability and robustness of our approach. The code and models are available at https://github.com/SandAI-org/MAGI-1 and https://github.com/SandAI-org/MagiAttention. The product can be accessed at https://sand.ai.

Large Language Models (LLMs) face significant challenges in long-context processing, including quadratic computational costs, information forgetting, and the context fragmentation inherent in retrieval-augmented generation (RAG). We propose a cognitively inspired framework for efficient long-context inference based on chunk-wise compression and selective memory recall, rather than processing all raw tokens. The framework segments long inputs into chunks and encodes each chunk into compressed memory representations using a learned compressor. A gating module dynamically selects relevant memory blocks, which are then iteratively processed by a reasoning module with an evolving working memory to solve downstream tasks. The compressor and reasoner are jointly optimized via end-to-end reinforcement learning, while the gating module is trained separately as a classifier. Experimental results show that the proposed method achieves competitive accuracy on multi-hop reasoning benchmarks such as RULER-HQA, extrapolates context length from 7K to 1.75M tokens, and offers a favorable accuracy-efficiency trade-off compared to strong long-context baselines. In particular, it achieves up to a 2 times reduction in peak GPU memory usage and a 6 times inference speedup over MemAgent.

Diffusion-based talking head generation has achieved remarkable visual quality, yet scaling it to long-term videos remains challenging. The widely adopted chunk-wise paradigm introduces two fundamental failures: (1) temporal-spatial misalignment between static identity references and dynamic audio streams, and (2) cascading identity drift propagated through self-generated continuity references across chunks. To address both issues, we propose AsymTalker, a novel diffusion-based talking head generation method comprising Temporal Reference Encoding (TRE) and Asymmetric Knowledge Distillation (AKD). First, TRE mitigates temporal-spatial misalignment by transforming the static identity image into a temporally coherent latent representation through encoding of a temporally replicated pseudo-video, without introducing additional parameters. Second, AKD resolves the inherent conditioning dilemma in chunk-wise training: using ground-truth references causes train-inference mismatch, while self-generated references entangle supervision with identity drift. Our asymmetric design circumvents this by anchoring the teacher model with ground-truth continuity references to provide drift-free, chunk-level supervision, thereby avoiding the teacher bottleneck. Meanwhile, the student model learns under inference-aligned conditions, conditioned only on self-generated references, and is trained via distribution matching to preserve identity over long horizons. Extensive experiments show AsymTalker achieves state-of-the-art results on HDTF and VFHQ. It guarantees high-fidelity, identity-consistent synthesis over 600-second videos and reaches a real-time inference speed of 66 FPS.

Real-time portrait animation is essential for interactive applications such as virtual assistants and live avatars, requiring high visual fidelity, temporal coherence, ultra-low latency, and responsive control from dynamic inputs like reference images and driving signals. While diffusion-based models achieve strong quality, their non-causal nature hinders streaming deployment. Causal autoregressive video generation approaches enable efficient frame-by-frame generation but suffer from error accumulation, motion discontinuities at chunk boundaries, and degraded long-term consistency. In this work, we present a novel streaming framework named Knot Forcing for real-time portrait animation that addresses these challenges through three key designs: (1) a chunk-wise generation strategy with global identity preservation via cached KV states of the reference image and local temporal modeling using sliding window attention; (2) a temporal knot module that overlaps adjacent chunks and propagates spatio-temporal cues via image-to-video conditioning to smooth inter-chunk motion transitions; and (3) A "running ahead" mechanism that dynamically updates the reference frame's temporal coordinate during inference, keeping its semantic context ahead of the current rollout frame to support long-term coherence. Knot Forcing enables high-fidelity, temporally consistent, and interactive portrait animation over infinite sequences, achieving real-time performance with strong visual stability on consumer-grade GPUs.

Standard Autoregressive Video LLMs inevitably suffer from causal masking biases that hinder global spatiotemporal modeling, leading to suboptimal understanding efficiency. We propose VidLaDA, a Video LLM based on Diffusion Language Model utilizing bidirectional attention to capture bidirectional dependencies. To further tackle the inference bottleneck of diffusion decoding on massive video tokens, we introduce MARS-Cache. This framework accelerates inference by combining asynchronous visual cache refreshing with frame-wise chunk attention, effectively pruning redundancy while preserving global connectivity via anchor tokens. Extensive experiments show VidLaDA outperforms diffusion baselines and rivals state-of-the-art autoregressive models (e.g., Qwen2.5-VL and LLaVA-Video), with MARS-Cache delivering over 12x speedup without compromising reasoning accuracy. Code and checkpoints are open-sourced at https://github.com/ziHoHe/VidLaDA.

Many use cases require retrieving smaller portions of text, and dense vector-based retrieval systems often perform better with shorter text segments, as the semantics are less likely to be "over-compressed" in the embeddings. Consequently, practitioners often split text documents into smaller chunks and encode them separately. However, chunk embeddings created in this way can lose contextual information from surrounding chunks, resulting in suboptimal representations. In this paper, we introduce a novel method called "late chunking," which leverages long context embedding models to first embed all tokens of the long text, with chunking applied after the transformer model and just before mean pooling. The resulting chunk embeddings capture the full contextual information, leading to superior results across various retrieval tasks without the need for additional training. Moreover, our method is generic enough to be applied to any long-context embedding model.

Transformer-based large models excel in natural language processing and computer vision, but face severe computational inefficiencies due to the self-attention's quadratic complexity with input tokens. Recently, researchers have proposed a series of methods based on block selection and compression to alleviate this problem, but they either have issues with semantic incompleteness or poor training-inference efficiency. To comprehensively address these challenges, we propose ChunkLLM, a lightweight and pluggable training framework. Specifically, we introduce two components: QK Adapter (Q-Adapter and K-Adapter) and Chunk Adapter. The former is attached to each Transformer layer, serving dual purposes of feature compression and chunk attention acquisition. The latter operates at the bottommost layer of the model, functioning to detect chunk boundaries by leveraging contextual semantic information. During the training phase, the parameters of the backbone remain frozen, with only the QK Adapter and Chunk Adapter undergoing training. Notably, we design an attention distillation method for training the QK Adapter, which enhances the recall rate of key chunks. During the inference phase, chunk selection is triggered exclusively when the current token is detected as a chunk boundary, thereby accelerating model inference. Experimental evaluations are conducted on a diverse set of long-text and short-text benchmark datasets spanning multiple tasks. ChunkLLM not only attains comparable performance on short-text benchmarks but also maintains 98.64% of the performance on long-context benchmarks while preserving a 48.58% key-value cache retention rate. Particularly, ChunkLLM attains a maximum speedup of 4.48x in comparison to the vanilla Transformer in the processing of 120K long texts.

Chunking strategies significantly impact the effectiveness of Retrieval-Augmented Generation (RAG) systems. Existing methods operate within fixed-granularity paradigms that rely on static boundary identification, limiting their adaptability to diverse query requirements. This paper presents FreeChunker, a Cross-Granularity Encoding Framework that fundamentally transforms the traditional chunking paradigm: the framework treats sentences as atomic units and shifts from static chunk segmentation to flexible retrieval supporting arbitrary sentence combinations. This paradigm shift not only significantly reduces the computational overhead required for semantic boundary detection but also enhances adaptability to complex queries. Experimental evaluation on LongBench V2 demonstrates that FreeChunker achieves superior retrieval performance compared to traditional chunking methods, while significantly outperforming existing approaches in computational efficiency.

Deploying large language models (LLMs) on edge devices presents significant challenges due to the substantial computational overhead and memory requirements. Activation sparsification can mitigate these challenges by reducing the number of activated neurons during inference. Existing methods typically employ thresholding-based sparsification based on the statistics of activation tensors. However, these methods do not explicitly model the impact of activation sparsification on performance, leading to suboptimal performance degradation. To address this issue, this paper reformulates the activation sparsification problem by introducing a new objective that optimizes the sparsification decisions. Building on this reformulation, we propose CHESS, a general activation sparsification approach via CHannel-wise thrEsholding and Selective Sparsification. First, channel-wise thresholding assigns a unique threshold to each activation channel in the feed-forward network (FFN) layers. Then, selective sparsification involves applying thresholding-based activation sparsification to specific layers within the attention modules. Finally, we detail the implementation of sparse kernels to accelerate LLM inference. Experimental results demonstrate that the proposed CHESS achieves lower performance degradation over 8 downstream tasks while activating fewer parameters compared to existing methods, thus speeding up the LLM inference by up to 1.27x.

Retrieval-augmented generation (RAG) for long-context question answering is bottlenecked by inference-time prefilling over large retrieved contexts. A common strategy is to precompute key-value (KV) caches for individual documents and selectively recompute a small subset of tokens to restore global causal dependencies, but existing methods rely on heuristics or representation discrepancies without modeling whether selected tokens can effectively influence generation. We cast selective KV recomputation as an information flow problem and show that a simple attention-norm signal from the query reliably identifies tokens that are both semantically relevant and structurally positioned to propagate information, when computed under an inference-consistent RoPE geometry. We therefore reconstruct global positional assignments for retrieved chunks and introduce an information-flow-guided chunk reordering strategy. Experiments on LLM and VLM benchmarks demonstrate consistent gains over prior methods under comparable efficiency budgets.

To reduce memory costs in long-context inference with Large Language Models (LLMs), many recent works focus on compressing the key-value (KV) cache of different tokens. However, we identify that the previous KV cache compression methods measure token importance individually, neglecting the dependency between different tokens in the real-world language characterics. In light of this, we introduce ChunkKV, grouping the tokens in a chunk as a basic compressing unit, and retaining the most informative semantic chunks while discarding the less important ones. Furthermore, observing that ChunkKV exhibits higher similarity in the preserved indices across different layers, we propose layer-wise index reuse to further reduce computational overhead. We evaluated ChunkKV on cutting-edge long-context benchmarks including LongBench and Needle-In-A-HayStack, as well as the GSM8K and JailbreakV in-context learning benchmark. Our experiments with instruction tuning and multi-step reasoning (O1 and R1) LLMs, achieve up to 10\% performance improvement under aggressive compression ratios compared to existing methods.

Chunking is a crucial preprocessing step in retrieval-augmented generation (RAG) systems, significantly impacting retrieval effectiveness across diverse datasets. In this study, we systematically evaluate fixed-size chunking strategies and their influence on retrieval performance using multiple embedding models. Our experiments, conducted on both short-form and long-form datasets, reveal that chunk size plays a critical role in retrieval effectiveness -- smaller chunks (64-128 tokens) are optimal for datasets with concise, fact-based answers, whereas larger chunks (512-1024 tokens) improve retrieval in datasets requiring broader contextual understanding. We also analyze the impact of chunking on different embedding models, finding that they exhibit distinct chunking sensitivities. While models like Stella benefit from larger chunks, leveraging global context for long-range retrieval, Snowflake performs better with smaller chunks, excelling at fine-grained, entity-based matching. Our results underscore the trade-offs between chunk size, embedding models, and dataset characteristics, emphasizing the need for improved chunk quality measures, and more comprehensive datasets to advance chunk-based retrieval in long-document Information Retrieval (IR).

In this paper, we introduce Writing in the Margins (WiM), a new inference pattern for Large Language Models designed to optimize the handling of long input sequences in retrieval-oriented tasks. This approach leverages the chunked prefill of the key-value cache to perform segment-wise inference, which enables efficient processing of extensive contexts along with the generation and classification of intermediate information ("margins") that guide the model towards specific tasks. This method increases computational overhead marginally while significantly enhancing the performance of off-the-shelf models without the need for fine-tuning. Specifically, we observe that WiM provides an average enhancement of 7.5% in accuracy for reasoning skills (HotpotQA, MultiHop-RAG) and more than a 30.0% increase in the F1-score for aggregation tasks (CWE). Additionally, we show how the proposed pattern fits into an interactive retrieval design that provides end-users with ongoing updates about the progress of context processing, and pinpoints the integration of relevant information into the final response. We release our implementation of WiM using Hugging Face Transformers library at https://github.com/writer/writing-in-the-margins.

Retrieval-Augmented Generation (RAG), while serving as a viable complement to large language models (LLMs), often overlooks the crucial aspect of text chunking within its pipeline, which impacts the quality of knowledge-intensive tasks. This paper introduces the concept of Meta-Chunking, which refers to a granularity between sentences and paragraphs, consisting of a collection of sentences within a paragraph that have deep linguistic logical connections. To implement Meta-Chunking, we designed two strategies based on LLMs: Margin Sampling Chunking and Perplexity Chunking. The former employs LLMs to perform binary classification on whether consecutive sentences need to be segmented, making decisions based on the probability difference obtained from margin sampling. The latter precisely identifies text chunk boundaries by analyzing the characteristics of perplexity distribution. Additionally, considering the inherent complexity of different texts, we propose a strategy that combines Meta-Chunking with dynamic merging to achieve a balance between fine-grained and coarse-grained text chunking. Experiments conducted on eleven datasets demonstrate that Meta-Chunking can more efficiently improve the performance of single-hop and multi-hop question answering based on RAG. For instance, on the 2WikiMultihopQA dataset, it outperforms similarity chunking by 1.32 while only consuming 45.8% of the time. Our code is available at https://github.com/IAAR-Shanghai/Meta-Chunking.

Large Language Models (LLMs) have demonstrated remarkable generation capabilities but often struggle to access up-to-date information, which can lead to hallucinations. Retrieval-Augmented Generation (RAG) addresses this issue by incorporating knowledge from external databases, enabling more accurate and relevant responses. Due to the context window constraints of LLMs, it is impractical to input the entire external database context directly into the model. Instead, only the most relevant information, referred to as chunks, is selectively retrieved. However, current RAG research faces three key challenges. First, existing solutions often select each chunk independently, overlooking potential correlations among them. Second, in practice the utility of chunks is non-monotonic, meaning that adding more chunks can decrease overall utility. Traditional methods emphasize maximizing the number of included chunks, which can inadvertently compromise performance. Third, each type of user query possesses unique characteristics that require tailored handling, an aspect that current approaches do not fully consider. To overcome these challenges, we propose a cost constrained retrieval optimization system CORAG for retrieval-augmented generation. We employ a Monte Carlo Tree Search (MCTS) based policy framework to find optimal chunk combinations sequentially, allowing for a comprehensive consideration of correlations among chunks. Additionally, rather than viewing budget exhaustion as a termination condition, we integrate budget constraints into the optimization of chunk combinations, effectively addressing the non-monotonicity of chunk utility.

A recent trend in LLMs is developing recurrent sub-quadratic models that improve long-context processing efficiency. We investigate leading large long-context models, focusing on how their fixed-size recurrent memory affects their performance. Our experiments reveal that, even when these models are trained for extended contexts, their use of long contexts remains underutilized. Specifically, we demonstrate that a chunk-based inference procedure, which identifies and processes only the most relevant portion of the input can mitigate recurrent memory failures and be effective for many long-context tasks: On LongBench, our method improves the overall performance of Falcon3-Mamba-Inst-7B by 14%, Falcon-Mamba-Inst-7B by 28%, RecurrentGemma-IT-9B by 50%, and RWKV6-Finch-7B by 51%. Surprisingly, this simple approach also leads to state-of-the-art results in the challenging LongBench v2 benchmark, showing competitive performance with equivalent size Transformers. Furthermore, our findings raise questions about whether recurrent models genuinely exploit long-range dependencies, as our single-chunk strategy delivers stronger performance - even in tasks that presumably require cross-context relations.

Selecting the best response from multiple small-model samples using a stronger scorer is a simple inference-time strategy, but fails when the small model has already committed to incorrect reasoning paths. PRM guided search avoids this by scoring candidate continuations during generation, but requires a reward model trained with step-level labels. We propose Chunk-Level Guided Generation, a training-free alternative that uses an off-the-shelf large language model as a process scorer. At each step, a small model samples k fixed-length candidate chunks, while the larger model scores the candidates using likelihoods without generating any text. The selected chunk is committed before the next step, steering generation before errors can propagate. We instantiate this framework with two selection rules: Likelihood-Guided Selection (LGS), which selects the chunk with the highest length-normalized large-model log-probability, and Contrastive-Guided Selection (CGS), which subtracts the small model's log-probability to favor chunks where the large model's preference diverges from the small model's. We show that scoring variable-length reasoning steps with large-model likelihoods is unreliable due to a systematic length bias that persists even after length normalization, and that fixed-length chunks avoid this confound. On GSM8K, MATH, Minerva Math, AMC23, and AIME24 with Qwen2.5-1.5B guided by Qwen2.5-32B and Llama-3.2-1B guided by Llama-3.1-70B, CGS outperforms majority voting by up to 28 pp and, under matched guidance budgets, matches or outperforms Qwen2.5-Math-PRM-72B guided search on most benchmarks without reward-model training. With Qwen2.5-7B guided by Qwen2.5-72B, CGS reaches 81.8% on MATH and 63.6% on Minerva Math at k=16, surpassing majority voting by 4--6 pp. Finally, Chunk-Level Guided Generation produces substantially shorter reasoning traces than PRM guided search.

Retrieval-Augmented Generation (RAG) systems using large language models (LLMs) often generate inaccurate responses due to the retrieval of irrelevant or loosely related information. Existing methods, which operate at the document level, fail to effectively filter out such content. We propose LLM-driven chunk filtering, ChunkRAG, a framework that enhances RAG systems by evaluating and filtering retrieved information at the chunk level. Our approach employs semantic chunking to divide documents into coherent sections and utilizes LLM-based relevance scoring to assess each chunk's alignment with the user's query. By filtering out less pertinent chunks before the generation phase, we significantly reduce hallucinations and improve factual accuracy. Experiments show that our method outperforms existing RAG models, achieving higher accuracy on tasks requiring precise information retrieval. This advancement enhances the reliability of RAG systems, making them particularly beneficial for applications like fact-checking and multi-hop reasoning.

Retrieval-augmented generation (RAG) has demonstrated significant proficiency in conducting question-answering (QA) tasks within a specified corpus. Nonetheless, numerous failure instances of RAG in QA still exist. These failures are not solely attributable to the limitations of Large Language Models (LLMs); instead, they predominantly arise from the retrieval of inaccurate information for LLMs due to two limitations: (1) Current RAG methods segment the corpus without considering semantics, making it difficult to find relevant context due to impaired correlation between questions and the segments. (2) There is a trade-off between missing essential context with fewer context retrieved and getting irrelevant context with more context retrieved. In this paper, we introduce a RAG framework (SAGE), to overcome these limitations. First, to address the segmentation issue without considering semantics, we propose to train a semantic segmentation model. This model is trained to segment the corpus into semantically complete chunks. Second, to ensure that only the most relevant chunks are retrieved while the irrelevant ones are ignored, we design a chunk selection algorithm to dynamically select chunks based on the decreasing speed of the relevance score, leading to a more relevant selection. Third, to further ensure the precision of the retrieved chunks, we propose letting LLMs assess whether retrieved chunks are excessive or lacking and then adjust the amount of context accordingly. Experiments show that SAGE outperforms baselines by 61.25% in the quality of QA on average. Moreover, by avoiding retrieving noisy context, SAGE lowers the cost of the tokens consumed in LLM inference and achieves a 49.41% enhancement in cost efficiency on average. Additionally, our work offers valuable insights for boosting RAG.

A limitation of modern document retrieval embedding methods is that they typically encode passages (chunks) from the same documents independently, often overlooking crucial contextual information from the rest of the document that could greatly improve individual chunk representations. In this work, we introduce ConTEB (Context-aware Text Embedding Benchmark), a benchmark designed to evaluate retrieval models on their ability to leverage document-wide context. Our results show that state-of-the-art embedding models struggle in retrieval scenarios where context is required. To address this limitation, we propose InSeNT (In-sequence Negative Training), a novel contrastive post-training approach which combined with late chunking pooling enhances contextual representation learning while preserving computational efficiency. Our method significantly improves retrieval quality on ConTEB without sacrificing base model performance. We further find chunks embedded with our method are more robust to suboptimal chunking strategies and larger retrieval corpus sizes. We open-source all artifacts at https://github.com/illuin-tech/contextual-embeddings.

Large language models (LLMs) have achieved impressive performance in numerous domains but often struggle to process lengthy inputs effectively and efficiently due to limited length generalization and attention's quadratic computational demands. Many sought to mitigate this by restricting the attention window within the pre-trained length. However, these methods introduce new issues such as ignoring the middle context and requiring additional training. To address these problems, we propose LongHeads, a training-free framework that enhances LLM's long context ability by unlocking multi-head attention's untapped potential. Instead of allowing each head to attend to the full sentence, which struggles with generalizing to longer sequences due to out-of-distribution (OOD) issues, we allow each head to process in-distribution length by selecting and attending to important context chunks. To this end, we propose a chunk selection strategy that relies on the inherent correlation between the query and the key representations, efficiently distributing context chunks to different heads. In this way, each head ensures it can effectively process attended tokens within the trained length, while different heads in different layers can collectively process longer contexts. LongHeads works efficiently in linear time, fits seamlessly with many LLMs that use relative positional encoding. Our extensive empirical analyses verify LongHeads's efficacy in extending the usable context window for existing models, showcasing its promise for enhancing long text understanding.

Retrieval-Augmented Generation (RAG), while serving as a viable complement to large language models (LLMs), often overlooks the crucial aspect of text chunking within its pipeline. This paper initially introduces a dual-metric evaluation method, comprising Boundary Clarity and Chunk Stickiness, to enable the direct quantification of chunking quality. Leveraging this assessment method, we highlight the inherent limitations of traditional and semantic chunking in handling complex contextual nuances, thereby substantiating the necessity of integrating LLMs into chunking process. To address the inherent trade-off between computational efficiency and chunking precision in LLM-based approaches, we devise the granularity-aware Mixture-of-Chunkers (MoC) framework, which consists of a three-stage processing mechanism. Notably, our objective is to guide the chunker towards generating a structured list of chunking regular expressions, which are subsequently employed to extract chunks from the original text. Extensive experiments demonstrate that both our proposed metrics and the MoC framework effectively settle challenges of the chunking task, revealing the chunking kernel while enhancing the performance of the RAG system.

Transformer-based embedding models suffer from quadratic computational and linear memory complexity, limiting their utility for long sequences. We propose recurrent architectures as an efficient alternative, introducing a vertically chunked inference strategy that enables fast embedding generation with memory usage that becomes constant in the input length once it exceeds the vertical chunk size. By fine-tuning Mamba2 models, we demonstrate their viability as general-purpose text embedders, achieving competitive performance across a range of benchmarks while maintaining a substantially smaller memory footprint compared to transformer-based counterparts. We empirically validate the applicability of our inference strategy to Mamba2, RWKV, and xLSTM models, confirming consistent runtime-memory trade-offs across architectures and establishing recurrent models as a compelling alternative to transformers for efficient embedding generation.

Language models are increasingly used to reason over content they were not trained on, such as new documents, evolving knowledge, and user-specific data. A common approach is retrieval-augmented generation (RAG), which stores verbatim documents externally (as chunks) and retrieves only a relevant subset at inference time for an LLM to reason over. However, this results in inefficient usage of test-time compute (LLM repeatedly reasons over the same documents); moreover, chunk retrieval can inject irrelevant context that increases unsupported generation. We propose a human-like non-parametric continual learning framework, where the base model remains fixed, and learning occurs by integrating each new experience into an external semantic memory state that accumulates and consolidates itself continually. We present Panini, which realizes this by representing documents as Generative Semantic Workspaces (GSW) -- an entity- and event-aware network of question-answer (QA) pairs, sufficient for an LLM to reconstruct the experienced situations and mine latent knowledge via reasoning-grounded inference chains on the network. Given a query, Panini only traverses the continually-updated GSW (not the verbatim documents or chunks), and retrieves the most likely inference chains. Across six QA benchmarks, Panini achieves the highest average performance, 5%-7% higher than other competitive baselines, while using 2-30x fewer answer-context tokens, supports fully open-source pipelines, and reduces unsupported answers on curated unanswerable queries. The results show that efficient and accurate structuring of experiences at write time -- as achieved by the GSW framework -- yields both efficiency and reliability gains at read time. Code is available at https://github.com/roychowdhuryresearch/gsw-memory.

Retrieval-augmented generation (RAG) over long documents typically involves splitting the text into smaller chunks, which serve as the basic units for retrieval. However, due to dependencies across the original document, contextual information is often essential for accurately interpreting each chunk. To address this, prior work has explored encoding longer context windows to produce embeddings for longer chunks. Despite these efforts, gains in retrieval and downstream tasks remain limited. This is because (1) longer chunks strain the capacity of embedding models due to the increased amount of information they must encode, and (2) many real-world applications still require returning localized evidence due to constraints on model or human bandwidth. We propose an alternative approach to this challenge by representing short chunks in a way that is conditioned on a broader context window to enhance retrieval performance -- i.e., situating a chunk's meaning within its context. We further show that existing embedding models are not well-equipped to encode such situated context effectively, and thus introduce a new training paradigm and develop the situated embedding models (SitEmb). To evaluate our method, we curate a book-plot retrieval dataset specifically designed to assess situated retrieval capabilities. On this benchmark, our SitEmb-v1 model based on BGE-M3 substantially outperforms state-of-the-art embedding models, including several with up to 7-8B parameters, with only 1B parameters. Our 8B SitEmb-v1.5 model further improves performance by over 10% and shows strong results across different languages and several downstream applications.

Generative AI models exhibit remarkable potential; however, hallucinations across various tasks present a significant challenge, particularly for longer inputs that current approaches struggle to address effectively. We introduce SCALE (Source Chunking Approach for Large-scale inconsistency Evaluation), a task-agnostic model for detecting factual inconsistencies using a novel chunking strategy. Specifically, SCALE is a Natural Language Inference (NLI) based model that uses large text chunks to condition over long texts. This approach achieves state-of-the-art performance in factual inconsistency detection for diverse tasks and long inputs. Additionally, we leverage the chunking mechanism and employ a novel algorithm to explain SCALE's decisions through relevant source sentence retrieval. Our evaluations reveal that SCALE outperforms existing methods on both standard benchmarks and a new long-form dialogue dataset ScreenEval we constructed. Moreover, SCALE surpasses competitive systems in efficiency and model explanation evaluations. We have released our code and data publicly to GitHub.

In Retrieval-Augmented Generation applications, the Information Retrieval part is central as it provides the contextual information that enables a Large Language Model to generate an appropriate and truthful response. High quality parsing and chunking are critical as efficient data segmentation directly impacts downstream tasks, i.e. Information Retrieval and answer generation. In this paper, we introduce ChunkNorris, a novel heuristic-based technique designed to optimise the parsing and chunking of PDF documents. Our approach does not rely on machine learning and employs a suite of simple yet effective heuristics to achieve high performance with minimal computational overhead. We demonstrate the efficiency of ChunkNorris through a comprehensive benchmark against existing parsing and chunking methods, evaluating criteria such as execution time, energy consumption, and retrieval accuracy. We propose an open-access dataset to produce our results. ChunkNorris outperforms baseline and more advanced techniques, offering a practical and efficient alternative for Information Retrieval tasks. Therefore, this research highlights the potential of heuristic-based methods for real-world, resource-constrained RAG use cases.

Retrieving external knowledge and prompting large language models with relevant information is an effective paradigm to enhance the performance of question-answering tasks. Previous research typically handles paragraphs from external documents in isolation, resulting in a lack of context and ambiguous references, particularly in multi-document and complex tasks. To overcome these challenges, we propose a new retrieval framework IIER, that leverages Inter-chunk Interactions to Enhance Retrieval. This framework captures the internal connections between document chunks by considering three types of interactions: structural, keyword, and semantic. We then construct a unified Chunk-Interaction Graph to represent all external documents comprehensively. Additionally, we design a graph-based evidence chain retriever that utilizes previous paths and chunk interactions to guide the retrieval process. It identifies multiple seed nodes based on the target question and iteratively searches for relevant chunks to gather supporting evidence. This retrieval process refines the context and reasoning chain, aiding the large language model in reasoning and answer generation. Extensive experiments demonstrate that IIER outperforms strong baselines across four datasets, highlighting its effectiveness in improving retrieval and reasoning capabilities.

Recent studies have demonstrated the effectiveness of using large language language models (LLMs) in passage ranking. The listwise approaches, such as RankGPT, have become new state-of-the-art in this task. However, the efficiency of RankGPT models is limited by the maximum context length and relatively high latency of LLM inference. To address these issues, in this paper, we propose PE-Rank, leveraging the single passage embedding as a good context compression for efficient listwise passage reranking. By treating each passage as a special token, we can directly input passage embeddings into LLMs, thereby reducing input length. Additionally, we introduce an inference method that dynamically constrains the decoding space to these special tokens, accelerating the decoding process. For adapting the model to reranking, we employ listwise learning to rank loss for training. Evaluation results on multiple benchmarks demonstrate that PE-Rank significantly improves efficiency in both prefilling and decoding, while maintaining competitive ranking effectiveness. {The Code is available at https://github.com/liuqi6777/pe_rank.}

Attention efficiency is critical to large language model (LLM) inference. While prior advances optimize attention execution for individual requests (e.g., FlashAttention), production LLM serving relies on batching requests with highly heterogeneous sequence lengths for high serving throughput. This mismatch induces severe computation and I/O imbalance, exacerbates stragglers, and underutilizes GPU resources. We present PackInfer, a kernel-level attention framework that enables compute- and I/O-aware execution for heterogeneous batched inference. PackInfer orchestrates batched requests into load-balanced execution groups, effectively saturating GPU utilization by packing multiple requests into unified kernel launches. By constructing attention kernels directly over packed query-key regions, PackInfer eliminates redundant computation and balances thread-block execution. It then incorporates I/O-aware grouping that co-locates shared-prefix requests and reorganizes KV caches into group-contiguous layouts, reducing memory fragmentation and redundant data movement as generation evolves. Evaluations on real-world workloads show that PackInfer reduces inference latency by 13.0-20.1%, and improves throughput by 20% compared to the state-of-the-art FlashAttention.

Retrieval-augmented generation is moving beyond text into long, egocentric video, where systems must select query-relevant chunks across multiple modalities and temporal granularities. Yet progress in VideoRAG is limited by two gaps: existing benchmarks allow queries to be answered without the video, obscuring retrieval errors, and prior methods apply a single modality-granularity configuration per query, ignoring chunk-level variability. We address both by introducing V-RAGBench, a benchmark of langlequery, evidence chunk, answerrangle triplets that enables faithful, decoupled evaluation of retrieval and generation, and CARVE, a simple method that runs parallel retrievers across configurations and employs chunk-adaptive reranking to identify the winning configuration for each chunk. Each chunk then enters the generator under its winning configuration selected during retrieval, yielding an interleaved evidence form where the chunk-level decision propagates across both stages. CARVE outperforms eight recent VideoRAG baselines, with the chunks supplied to the generator interleaving multiple configurations rather than sharing a single one, a behavior unattainable by query-level methods.

Diffusion language models (DLMs) generate text through iterative denoising, but inference requires full-sequence attention at every iteration, resulting in substantial redundant computation on masked tokens. Block-wise diffusion can reduce this cost, yet it typically relies on retraining and constrained update orders, limiting its direct applicability to pretrained DLMs. Our token-level analysis reveals pronounced structural locality in DLM inference. Decoding is driven by a small set of prefix-localized active tokens; the influence of distant undecoded context diminishes rapidly, and decoded tokens exhibit stage-wise temporal stability, enabling reuse of intermediate representations except for a brief post-decode transient. Motivated by these observations, we propose \placeholderThe source code is available at https://github.com/vhicrgit/Window-Diffusion., a window-based token pruning and caching method for inference. We maintain a local computation window that slides rightward as denoising progresses, and partition undecoded tokens into: (i) active tokens that are computed online, (ii) buffer tokens whose KV states are cached and periodically refreshed, and (iii) far-field tokens that are pruned outside the window. Computation is restricted to active and buffer tokens within the window, while far-field tokens are omitted at each stage. Experiments on LLaDA and Dream show that, under matched compute budgets, our method achieves up to 99times inference speedup while largely preserving generation performance.

Effectively processing long contexts is a critical challenge for language models. While standard Transformers are limited by quadratic complexity and poor length extrapolation, alternative architectures like sliding window attention and state space models sacrifice the ability to effectively utilize the full context due to their fixed-size memory. Chunk-based sparse attention has emerged as a promising paradigm for extreme length generalization, yet the key architectural principles underpinning its success are not yet fully understood. In this work, we present a systematic dissection of these models to identify the core components driving their performance. Through a unified framework and comprehensive ablation studies, we demonstrate that a combination of three design principles is critical: (1) an expressive, non-linear Chunk Encoder with a dedicated CLS token to produce representations for retrieval; (2) a Bypassing Residual Path to stably integrate retrieved global information without it being overridden by the local residual stream; and (3) enforced selection sparsity during pre-training to bridge the train-test distribution gap. We provide a theoretical motivation for intra-chunk information processing and landmark generation. By combining these principles, we establish a new state-of-the-art for training-free length extrapolation, successfully generalizing models trained on a 4K context to 32 million tokens on RULER and BABILong. Our findings provide a clear and empirically-grounded set of design principles for developing future, highly-capable long-context language models.

Retrieval-Augmented Generation (RAG) systems critically depend on effective document chunking strategies to balance retrieval quality, latency, and operational cost. Traditional chunking approaches, such as fixed-size, rule-based, or fully agentic chunking, often suffer from high token consumption, redundant text generation, limited scalability, and poor debuggability, especially for large-scale web content ingestion. In this paper, we propose Web Retrieval-Aware Chunking (W-RAC), a novel, cost-efficient chunking framework designed specifically for web-based documents. W-RAC decouples text extraction from semantic chunk planning by representing parsed web content as structured, ID-addressable units and leveraging large language models (LLMs) only for retrieval-aware grouping decisions rather than text generation. This significantly reduces token usage, eliminates hallucination risks, and improves system observability.Experimental analysis and architectural comparison demonstrate that W-RAC achieves comparable or better retrieval performance than traditional chunking approaches while reducing chunking-related LLM costs by an order of magnitude.

We study how document chunking choices impact the reliability of Retrieval-Augmented Generation (RAG) systems in industry. While practice often relies on heuristics, our end-to-end evaluation on Natural Questions systematically varies chunking method (token, sentence, semantic, code), chunk size, overlap, and context length. We use a standard industrial setup: SPLADE retrieval and a Mistral-8B generator. We derive actionable lessons for cost-efficient deployment: (i) overlap provides no measurable benefit and increases indexing cost; (ii) sentence chunking is the most cost-effective method, matching semantic chunking up to ~5k tokens; (iii) a "context cliff" reduces quality beyond ~2.5k tokens; and (iv) optimal context depends on the goal (semantic quality peaks at small contexts; exact match at larger ones).

We benchmark Google Embeddings (GE2), a Vertex-AI-hosted bi-encoder with 2,048-token context and explicit task-type conditioning, against five open-source alternatives: BGE-M3, E5-large, Multilingual-E5-large (mE5-L), LaBSE, and Paraphrase-Multilingual-MPNet (mMPNet). Evaluation covers four BEIR subsets, a synthetic Italian RAG corpus, a chunking ablation considering 5 sizes of tokens with three strategies, and per-query latency on commodity CPU hardware. GE2 ranks first on every task, achieving BEIR avg.nDCG@10 = 0.638 and IT-RAG-Bench nDCG@10 = 0.282, but at 231.6 ms median latency, it is roughly 14x slower than the fastest local models. mE5-L reaches within 0.003 nDCG of GE2 on Italian at 31 ms, making it the preferred option when sub-100 ms SLAs matter. A more striking finding concerns LaBSE, which, despite widespread multilingual deployment scores 0.188 average nDCG@10 on BEIR, below every dedicated retrieval model including mMPNet. Chunking experiments show that all six models saturate at 32-token chunks on our corpus, with semantic chunking providing measurable gains only at 16 tokens.

Chain-of-Thought (CoT) reasoning enhances large language models (LLMs) by enabling step-by-step problem-solving, yet its extension to Long-CoT introduces substantial computational overhead due to increased token length. Existing compression approaches -- instance-level and token-level -- either sacrifice essential local reasoning signals like reflection or yield incoherent outputs. To address these limitations, we propose R1-Compress, a two-stage chunk-level compression framework that preserves both local information and coherence. Our method segments Long-CoT into manageable chunks, applies LLM-driven inner-chunk compression, and employs an inter-chunk search mechanism to select the short and coherent sequence. Experiments on Qwen2.5-Instruct models across MATH500, AIME24, and GPQA-Diamond demonstrate that R1-Compress significantly reduces token usage while maintaining comparable reasoning accuracy. On MATH500, R1-Compress achieves an accuracy of 92.4%, with only a 0.6% drop compared to the Long-CoT baseline, while reducing token usage by about 20%. Source code will be available at https://github.com/w-yibo/R1-Compress

Speculative decoding (SD) has become a popular technique to accelerate Large Language Model (LLM) inference, yet its real-world effectiveness remains unclear as prior evaluations rely on research prototypes and unrealistically small batch sizes. We present, to our knowledge, the first systematic study of SD on a production-grade and widely deployed inference engine (vLLM), covering multiple SD variants (n-gram, EAGLE/EAGLE-3, Draft-Model, Multi-Token Prediction) across diverse workloads, model scales, and batch sizes. We analyze key factors governing SD performance, and quantify a theoretical upper bound on SD speedup. Our results show that verification by the target model dominates the execution, while acceptance length varies markedly across output token positions, requests, and datasets. Comparing measured performance with theoretical bounds reveals substantial gaps between observed and theoretical upper bounds, and we leverage this observation to highlight new research opportunities that our study opens up in improving SD.

As large language models (LLMs) evolve to handle increasingly longer contexts, serving inference requests for context lengths in the range of millions of tokens presents unique challenges. While existing techniques are effective for training, they fail to address the unique challenges of inference, such as varying prefill and decode phases and their associated latency constraints - like Time to First Token (TTFT) and Time Between Tokens (TBT). Furthermore, there are no long context inference solutions that allow batching requests to increase the hardware utilization today. In this paper, we propose three key innovations for efficient interactive long context LLM inference, without resorting to any approximation: adaptive chunking to reduce prefill overheads in mixed batching, Sequence Pipeline Parallelism (SPP) to lower TTFT, and KV Cache Parallelism (KVP) to minimize TBT. These contributions are combined into a 3D parallelism strategy, enabling Mnemosyne to scale interactive inference to context lengths at least up to 10 million tokens with high throughput enabled with batching. To our knowledge, Mnemosyne is the first to be able to achieve support for 10 million long context inference efficiently, while satisfying production-grade SLOs on TBT (30ms) on contexts up to and including 10 million.

Large language models (LLMs) have revolutionized the field of AI, demonstrating unprecedented capacity across various tasks. However, the inference process for LLMs comes with significant computational costs. In this paper, we propose an efficient LLM inference pipeline that harnesses the power of LLMs. Our approach begins by tapping into the potential of LLMs to accurately perceive and predict the response length with minimal overhead. By leveraging this information, we introduce an efficient sequence scheduling technique that groups queries with similar response lengths into micro-batches. We evaluate our approach on real-world instruction datasets using the LLaMA-based model, and our results demonstrate an impressive 86% improvement in inference throughput without compromising effectiveness. Notably, our method is orthogonal to other inference acceleration techniques, making it a valuable addition to many existing toolkits (e.g., FlashAttention, Quantization) for LLM inference.

Large language models (LLMs) have demonstrated remarkable capabilities across various tasks. However, their widespread application is hindered by the resource-intensive decoding process. To address this challenge, current approaches have incorporated additional decoding heads to enable parallel prediction of multiple subsequent tokens, thereby achieving inference acceleration. Nevertheless, the accuracy of these decoding heads falls short of the auto-regressive decoding approach. In light of these limitations, we propose Chimera, a novel framework specifically designed for speculative sampling. Within this framework, we introduce a lightweight draft model that effectively utilizes previously generated tokens to predict subsequent words. To ensure both accuracy and efficiency, we present two strategies within the lightweight draft model. Firstly, we focus on capturing short-range dependencies at the bottom layer. Secondly, we leverage the readily available representations from the original LLM.Through empirical evaluation on the Vicuna and LlaMA-2 series, Chimera demonstrates impressive results, achieving an average latency speedup ratio of 2.7x compared to the vanilla auto-regressive decoding approach. This highlights the potential of our proposed framework in significantly improving the efficiency of large language models during the decoding process.

The advent of 1-bit large language models (LLMs), led by BitNet b1.58, has spurred interest in ternary LLMs. Despite this, research and practical applications focusing on efficient edge inference for ternary LLMs remain scarce. To bridge this gap, we introduce Bitnet.cpp, an inference system optimized for BitNet b1.58 and ternary LLMs. Given that mixed-precision matrix multiplication (mpGEMM) constitutes the bulk of inference time in ternary LLMs, Bitnet.cpp incorporates a novel mpGEMM library to facilitate sub-2-bits-per-weight, efficient and lossless inference. The library features two core solutions: Ternary Lookup Table (TL), which addresses spatial inefficiencies of previous bit-wise methods, and Int2 with a Scale (I2_S), which ensures lossless edge inference, both enabling high-speed inference. Our experiments show that Bitnet.cpp achieves up to a 6.25x increase in speed over full-precision baselines and up to 2.32x over low-bit baselines, setting new benchmarks in the field. Additionally, we expand TL to element-wise lookup table (ELUT) for low-bit LLMs in the appendix, presenting both theoretical and empirical evidence of its considerable potential. Bitnet.cpp is publicly available at https://github.com/microsoft/BitNet/tree/paper , offering a sophisticated solution for the efficient and practical deployment of edge LLMs.

Large Language Models (LLMs) have attracted extensive attention due to their remarkable performance across various tasks. However, the substantial computational and memory requirements of LLM inference pose challenges for deployment in resource-constrained scenarios. Efforts within the field have been directed towards developing techniques aimed at enhancing the efficiency of LLM inference. This paper presents a comprehensive survey of the existing literature on efficient LLM inference. We start by analyzing the primary causes of the inefficient LLM inference, i.e., the large model size, the quadratic-complexity attention operation, and the auto-regressive decoding approach. Then, we introduce a comprehensive taxonomy that organizes the current literature into data-level, model-level, and system-level optimization. Moreover, the paper includes comparative experiments on representative methods within critical sub-fields to provide quantitative insights. Last but not least, we provide some knowledge summary and discuss future research directions.

Document chunking is a crucial component of Retrieval-Augmented Generation (RAG), as it directly affects the retrieval of relevant and precise context. Conventional fixed-length and recursive splitters often produce arbitrary, incoherent segments that fail to preserve semantic structure. Although semantic chunking has gained traction, its influence on generation quality remains underexplored. This paper introduces two efficient semantic chunking methods, Projected Similarity Chunking (PSC) and Metric Fusion Chunking (MFC), trained on PubMed data using three different embedding models. We further present an evaluation framework that measures the effect of chunking on both retrieval and generation by augmenting PubMedQA with full-text PubMed Central articles. Our results show substantial retrieval improvements (24x with PSC) in MRR and higher Hits@k on PubMedQA. We provide a comprehensive analysis, including statistical significance and response-time comparisons with common chunking libraries. Despite being trained on a single domain, PSC and MFC also generalize well, achieving strong out-of-domain generation performance across multiple datasets. Overall, our findings confirm that our semantic chunkers, especially PSC, consistently deliver superior performance.

Retrieval augmentation addresses many critical problems in large language models such as hallucination, staleness, and privacy leaks. However, running retrieval-augmented language models (LMs) is slow and difficult to scale due to processing large amounts of retrieved text. We introduce binary token representations (BTR), which use 1-bit vectors to precompute every token in passages, significantly reducing computation during inference. Despite the potential loss of accuracy, our new calibration techniques and training objectives restore performance. Combined with offline and runtime compression, this only requires 127GB of disk space for encoding 3 billion tokens in Wikipedia. Our experiments show that on five knowledge-intensive NLP tasks, BTR accelerates state-of-the-art inference by up to 4x and reduces storage by over 100x while maintaining over 95% task performance.

Optimizing inference for long-context Large Language Models (LLMs) is increasingly important due to the quadratic compute and linear memory complexity of Transformers. Existing approximation methods, such as key-value (KV) cache dropping, sparse attention, and prompt compression, typically rely on rough predictions of token or KV pair importance. We propose a novel framework for approximate LLM inference that leverages small draft models to more accurately predict the importance of tokens and KV pairs. Specifically, we introduce two instantiations of our proposed framework: (i) SpecKV, which leverages a draft output to accurately assess the importance of each KV pair for more effective KV cache dropping, and (ii) SpecPC, which uses the draft model's attention activations to identify and discard unimportant prompt tokens. To the best of our knowledge, this is the first work to use draft models for approximate LLM inference acceleration, extending their utility beyond traditional lossless speculative decoding. We motivate our methods with theoretical and empirical analyses, and show a strong correlation between the attention patterns of draft and target models. Extensive experiments on long-context benchmarks show that our methods consistently achieve higher accuracy than existing baselines, while preserving the same improvements in memory usage, latency, and throughput. Our code is available at https://github.com/furiosa-ai/draft-based-approx-llm.

The quadratic cost of attention hinders the scalability of long-context LLMs, especially in resource-constrained settings. Existing static sparse methods such as sliding windows or global tokens utilizes the sparsity of attention to reduce the cost of attention, but poorly adapts to the content-dependent variations in attention due to their staticity. While previous work has proposed several dynamic approaches to improve flexibility, they still depend on predefined templates or heuristic mechanisms. Such strategies reduce generality and prune tokens that remain contextually important, limiting their accuracy across diverse tasks. To tackle these bottlenecks of existing methods for long-context modeling, we introduce Dynamic Hierarchical Sparse Attention (DHSA), a data-driven framework that dynamically predicts attention sparsity online without retraining. Our proposed DHSA adaptively segments sequences into variable-length chunks, then computes chunk representations by aggregating the token embeddings within each chunk. To avoid the bias introduced by varying chunk lengths, we apply length-normalized aggregation that scales the averaged embeddings by the square root of the chunk size. Finally, DHSA upsamples the chunk-level similarity scores to token level similarities to calculate importance scores that determine which token-level interactions should be preserved. Our experiments on Gemma2 with Needle-in-a-Haystack Test and LongBench show that DHSA matches dense attention in accuracy, while reducing prefill latency by 20-60% and peak memory usage by 35%. Compared to other representative baselines such as block sparse attention, DHSA achieves consistently higher accuracy (6-18% relative gains) with comparable or lower cost, offering an efficient and adaptable solution for long-context on-device LLMs.

Large Language Models (LLMs) apply uniform computation to all tokens, despite language exhibiting highly non-uniform information density. This token-uniform regime wastes capacity on locally predictable spans while under-allocating computation to semantically critical transitions. We propose Dynamic Large Concept Models (DLCM), a hierarchical language modeling framework that learns semantic boundaries from latent representations and shifts computation from tokens to a compressed concept space where reasoning is more efficient. DLCM discovers variable-length concepts end-to-end without relying on predefined linguistic units. Hierarchical compression fundamentally changes scaling behavior. We introduce the first compression-aware scaling law, which disentangles token-level capacity, concept-level reasoning capacity, and compression ratio, enabling principled compute allocation under fixed FLOPs. To stably train this heterogeneous architecture, we further develop a decoupled μP parametrization that supports zero-shot hyperparameter transfer across widths and compression regimes. At a practical setting (R=4, corresponding to an average of four tokens per concept), DLCM reallocates roughly one-third of inference compute into a higher-capacity reasoning backbone, achieving a +2.69\% average improvement across 12 zero-shot benchmarks under matched inference FLOPs.

The effectiveness upper bound of retrieval-augmented generation (RAG) is fundamentally constrained by the semantic integrity and information granularity of text chunks in its knowledge base. To address these challenges, this paper proposes QChunker, which restructures the RAG paradigm from retrieval-augmentation to understanding-retrieval-augmentation. Firstly, QChunker models the text chunking as a composite task of text segmentation and knowledge completion to ensure the logical coherence and integrity of text chunks. Drawing inspiration from Hal Gregersen's "Questions Are the Answer" theory, we design a multi-agent debate framework comprising four specialized components: a question outline generator, text segmenter, integrity reviewer, and knowledge completer. This framework operates on the principle that questions serve as catalysts for profound insights. Through this pipeline, we successfully construct a high-quality dataset of 45K entries and transfer this capability to small language models. Additionally, to handle long evaluation chains and low efficiency in existing chunking evaluation methods, which overly rely on downstream QA tasks, we introduce a novel direct evaluation metric, ChunkScore. Both theoretical and experimental validations demonstrate that ChunkScore can directly and efficiently discriminate the quality of text chunks. Furthermore, during the text segmentation phase, we utilize document outlines for multi-path sampling to generate multiple candidate chunks and select the optimal solution employing ChunkScore. Extensive experimental results across four heterogeneous domains exhibit that QChunker effectively resolves aforementioned issues by providing RAG with more logically coherent and information-rich text chunks.

Retrieval-augmented generation (RAG) systems must balance retrieval granularity with contextual coherence, a challenge that existing methods address through LLM-guided chunking, single-level context expansion, or hierarchical summarization. These approaches variously depend on costly LLM calls during indexing or retrieval, limit context aggregation to a single granularity level, or introduce information loss through summarization. We present SproutRAG, an attention-guided hierarchical RAG framework that addresses this trade-off by organizing sentence-level chunks into progressively larger but semantically coherent units, using learned inter-sentence attention to construct a binary chunking tree. Unlike prior approaches that rely on external LLMs, fixed context expansion, or lossy summarization, SproutRAG learns which attention heads and layers best capture semantic document structure, enabling multi-granularity retrieval without additional LLM calls or compressed summaries. At retrieval time, SproutRAG uses hierarchical beam search to retrieve candidates at multiple granularities, capturing multi-sentence relevance beyond flat retrieval. The framework is trained end-to-end with a joint objective that improves both embeddings and tree structure. Experiments across four benchmarks spanning scientific, legal, and open-domain settings demonstrate that SproutRAG improves information efficiency (IE) by 6.1% on average over the strongest baseline. Code is available on https://github.com/AmirAbaskohi/SproutRAG.

One of the most striking findings in modern research on large language models (LLMs) is that scaling up compute during training leads to better results. However, less attention has been given to the benefits of scaling compute during inference. This survey focuses on these inference-time approaches. We explore three areas under a unified mathematical formalism: token-level generation algorithms, meta-generation algorithms, and efficient generation. Token-level generation algorithms, often called decoding algorithms, operate by sampling a single token at a time or constructing a token-level search space and then selecting an output. These methods typically assume access to a language model's logits, next-token distributions, or probability scores. Meta-generation algorithms work on partial or full sequences, incorporating domain knowledge, enabling backtracking, and integrating external information. Efficient generation methods aim to reduce token costs and improve the speed of generation. Our survey unifies perspectives from three research communities: traditional natural language processing, modern LLMs, and machine learning systems.

Breaking long documents into smaller segments is a fundamental challenge in information retrieval. Whether for search engines, question-answering systems, or retrieval-augmented generation (RAG), effective segmentation determines how well systems can locate and return relevant information. However, traditional methods, such as fixed-length or coherence-based segmentation, ignore user intent, leading to chunks that split answers or contain irrelevant noise. We introduce Intent-Driven Dynamic Chunking (IDC), a novel approach that uses predicted user queries to guide document segmentation. IDC leverages a Large Language Model to generate likely user intents for a document and then employs a dynamic programming algorithm to find the globally optimal chunk boundaries. This represents a novel application of DP to intent-aware segmentation that avoids greedy pitfalls. We evaluated IDC on six diverse question-answering datasets, including news articles, Wikipedia, academic papers, and technical documentation. IDC outperformed traditional chunking strategies on five datasets, improving top-1 retrieval accuracy by 5% to 67%, and matched the best baseline on the sixth. Additionally, IDC produced 40-60% fewer chunks than baseline methods while achieving 93-100% answer coverage. These results demonstrate that aligning document structure with anticipated information needs significantly boosts retrieval performance, particularly for long and heterogeneous documents.

In recent years, large language models have demonstrated remarkable performance across various natural language processing (NLP) tasks. However, deploying these models for real-world applications often requires efficient inference solutions to handle the computational demands. In this paper, we explore the utilization of CPUs for accelerating the inference of large language models. Specifically, we introduce a parallelized approach to enhance throughput by 1) Exploiting the parallel processing capabilities of modern CPU architectures, 2) Batching the inference request. Our evaluation shows the accelerated inference engine gives an 18-22x improvement in the generated token per sec. The improvement is more with longer sequence and larger models. In addition to this, we can also run multiple workers in the same machine with NUMA node isolation to further improvement in tokens/s. Table 2, we have received 4x additional improvement with 4 workers. This would also make Gen-AI based products and companies environment friendly, our estimates shows that CPU usage for Inference could reduce the power consumption of LLMs by 48.9% while providing production ready throughput and latency.

Modern NLP tasks increasingly rely on dense retrieval methods to access up-to-date and relevant contextual information. We are motivated by the premise that retrieval benefits from segments that can vary in size such that a content's semantic independence is better captured. We propose LumberChunker, a method leveraging an LLM to dynamically segment documents, which iteratively prompts the LLM to identify the point within a group of sequential passages where the content begins to shift. To evaluate our method, we introduce GutenQA, a benchmark with 3000 "needle in a haystack" type of question-answer pairs derived from 100 public domain narrative books available on Project Gutenberg. Our experiments show that LumberChunker not only outperforms the most competitive baseline by 7.37% in retrieval performance (DCG@20) but also that, when integrated into a RAG pipeline, LumberChunker proves to be more effective than other chunking methods and competitive baselines, such as the Gemini 1.5M Pro. Our Code and Data are available at https://github.com/joaodsmarques/LumberChunker

Retrieval-Augmented Generation (RAG) has become essential for large-scale code generation, grounding predictions in external code corpora to improve actuality. However, a critical yet underexplored aspect of RAG pipelines is chunking -- the process of dividing documents into retrievable units. Existing line-based chunking heuristics often break semantic structures, splitting functions or merging unrelated code, which can degrade generation quality. We propose chunking via Abstract Syntax Trees (\ourwork), a structure-aware method that recursively breaks large AST nodes into smaller chunks and merges sibling nodes while respecting size limits. This approach generates self-contained, semantically coherent units across programming languages and tasks, improving performance on diverse code generation tasks, e.g., boosting Recall@5 by 4.3 points on RepoEval retrieval and Pass@1 by 2.67 points on SWE-bench generation. Our work highlights the importance of structure-aware chunking for scaling retrieval-enhanced code intelligence.

Although Large Vision-Language Models (LVLMs) have achieved impressive results, their high computational cost poses a significant barrier to wider application. To enhance inference efficiency, most existing approaches depend on parameter-dependent or token-dependent strategies to reduce computational demands. However, these methods typically require complex training processes and struggle to consistently select the most relevant tokens. In this paper, we systematically analyze the above challenges and provide a series of valuable insights for inference acceleration. Based on these findings, we propose a novel framework, the Pruning All-Rounder (PAR). Different from previous works, PAR develops a meta-router to adaptively organize pruning flows across both tokens and layers. With a self-supervised learning manner, our method achieves a superior balance between performance and efficiency. Notably, PAR is highly flexible, offering multiple pruning versions to address a range of pruning scenarios. The code for this work will be made publicly available.

Long sequence modeling has gained broad interest as large language models (LLMs) continue to advance. Recent research has identified that a large portion of hidden states within the key-value caches of Transformer models can be discarded (also termed evicted) without affecting the perplexity performance in generating long sequences. However, we show that these methods, despite preserving perplexity performance, often drop information that is important for solving downstream tasks, a problem which we call information neglect. To address this issue, we introduce Chunked Instruction-aware State Eviction (CItruS), a novel modeling technique that integrates the attention preferences useful for a downstream task into the eviction process of hidden states. In addition, we design a method for chunked sequence processing to further improve efficiency. Our training-free method exhibits superior performance on long sequence comprehension and retrieval tasks over several strong baselines under the same memory budget, while preserving language modeling perplexity.

This paper presents a novel Chunking-Free In-Context (CFIC) retrieval approach, specifically tailored for Retrieval-Augmented Generation (RAG) systems. Traditional RAG systems often struggle with grounding responses using precise evidence text due to the challenges of processing lengthy documents and filtering out irrelevant content. Commonly employed solutions, such as document chunking and adapting language models to handle longer contexts, have their limitations. These methods either disrupt the semantic coherence of the text or fail to effectively address the issues of noise and inaccuracy in evidence retrieval. CFIC addresses these challenges by circumventing the conventional chunking process. It utilizes the encoded hidden states of documents for in-context retrieval, employing auto-aggressive decoding to accurately identify the specific evidence text required for user queries, eliminating the need for chunking. CFIC is further enhanced by incorporating two decoding strategies, namely Constrained Sentence Prefix Decoding and Skip Decoding. These strategies not only improve the efficiency of the retrieval process but also ensure that the fidelity of the generated grounding text evidence is maintained. Our evaluations of CFIC on a range of open QA datasets demonstrate its superiority in retrieving relevant and accurate evidence, offering a significant improvement over traditional methods. By doing away with the need for document chunking, CFIC presents a more streamlined, effective, and efficient retrieval solution, making it a valuable advancement in the field of RAG systems.

Retrieval-augmented generation (RAG) has become a transformative approach for enhancing large language models (LLMs) by grounding their outputs in external knowledge sources. Yet, a critical question persists: how can vast volumes of external knowledge be managed effectively within the input constraints of LLMs? Traditional methods address this by chunking external documents into smaller, fixed-size segments. While this approach alleviates input limitations, it often fragments context, resulting in incomplete retrieval and diminished coherence in generation. To overcome these shortcomings, two advanced techniques, late chunking and contextual retrieval, have been introduced, both aiming to preserve global context. Despite their potential, their comparative strengths and limitations remain unclear. This study presents a rigorous analysis of late chunking and contextual retrieval, evaluating their effectiveness and efficiency in optimizing RAG systems. Our results indicate that contextual retrieval preserves semantic coherence more effectively but requires greater computational resources. In contrast, late chunking offers higher efficiency but tends to sacrifice relevance and completeness.

We introduce the Byte Latent Transformer (BLT), a new byte-level LLM architecture that, for the first time, matches tokenization-based LLM performance at scale with significant improvements in inference efficiency and robustness. BLT encodes bytes into dynamically sized patches, which serve as the primary units of computation. Patches are segmented based on the entropy of the next byte, allocating more compute and model capacity where increased data complexity demands it. We present the first FLOP controlled scaling study of byte-level models up to 8B parameters and 4T training bytes. Our results demonstrate the feasibility of scaling models trained on raw bytes without a fixed vocabulary. Both training and inference efficiency improve due to dynamically selecting long patches when data is predictable, along with qualitative improvements on reasoning and long tail generalization. Overall, for fixed inference costs, BLT shows significantly better scaling than tokenization-based models, by simultaneously growing both patch and model size.

Retrieval-augmented generation (RAG) systems depend critically on how documents are chunked and searched. Fine-grained chunks can improve retrieval precision but expand the search space, increasing latency and cost; larger chunks reduce the number of candidates but make dense similarity less reliable, as the representation for each chunk mixes multiple topics and introduces more semantic noise. This trade-off becomes especially limiting in deep research tasks, where retrieval must be both fast and precise across large, heterogeneous corpora. We introduce MCompassRAG, a metadata-guided retrieval framework that uses topic-level signals as a semantic compass for selecting relevant evidence. Instead of relying only on cosine similarity between queries and noisy chunk embeddings, MCompassRAG enriches chunk representations with topic metadata in the same embedding space and trains a lightweight retriever through LLM-teacher distillation. At inference time, MCompassRAG performs topic-aware retrieval without additional LLM calls, improving both efficiency and evidence quality. Across six complex retrieval benchmarks, MCompassRAG improves information efficiency (IE) by 8.24% on average with over 5 times lower latency than the strongest efficient RAG baselines. Code is available on https://github.com/AmirAbaskohi/MCompassRAG.

Following recent successes in applying BERT to question answering, we explore simple applications to ad hoc document retrieval. This required confronting the challenge posed by documents that are typically longer than the length of input BERT was designed to handle. We address this issue by applying inference on sentences individually, and then aggregating sentence scores to produce document scores. Experiments on TREC microblog and newswire test collections show that our approach is simple yet effective, as we report the highest average precision on these datasets by neural approaches that we are aware of.

Recent advances in Retrieval-Augmented Generation (RAG) systems have popularized semantic chunking, which aims to improve retrieval performance by dividing documents into semantically coherent segments. Despite its growing adoption, the actual benefits over simpler fixed-size chunking, where documents are split into consecutive, fixed-size segments, remain unclear. This study systematically evaluates the effectiveness of semantic chunking using three common retrieval-related tasks: document retrieval, evidence retrieval, and retrieval-based answer generation. The results show that the computational costs associated with semantic chunking are not justified by consistent performance gains. These findings challenge the previous assumptions about semantic chunking and highlight the need for more efficient chunking strategies in RAG systems.

Long-context inference for Large Language Models (LLMs) is heavily limited by high computational demands. While several existing methods optimize attention computation, they still process the full set of hidden states at each layer, limiting overall efficiency. In this work, we propose SlimInfer, an innovative framework that aims to accelerate inference by directly pruning less critical prompt tokens during the forward pass. Our key insight is an information diffusion phenomenon: As information from critical tokens propagates through layers, it becomes distributed across the entire sequence. This diffusion process suggests that LLMs can maintain their semantic integrity when excessive tokens, even including these critical ones, are pruned in hidden states. Motivated by this, SlimInfer introduces a dynamic fine-grained pruning mechanism that accurately removes redundant tokens of hidden state at intermediate layers. This layer-wise pruning naturally enables an asynchronous KV cache manager that prefetches required token blocks without complex predictors, reducing both memory usage and I/O costs. Extensive experiments show that SlimInfer can achieve up to 2.53times time-to-first-token (TTFT) speedup and 1.88times end-to-end latency reduction for LLaMA3.1-8B-Instruct on a single RTX 4090, without sacrificing performance on LongBench. Our code will be released upon acceptance.

The quadratic computational complexity of the attention mechanism in current Large Language Models (LLMs) renders inference with long contexts prohibitively expensive. To address this challenge, various approaches aim to retain critical portions of the context to optimally approximate Full Attention (FA) through Key-Value (KV) compression or Sparse Attention (SA), enabling the processing of virtually unlimited text lengths in a streaming manner. However, these methods struggle to achieve performance levels comparable to FA, particularly in retrieval tasks. In this paper, our analysis of attention head patterns reveals that LLMs' attention distributions show strong local correlations, naturally reflecting a chunking mechanism for input context. We propose Ltri-LLM framework, which divides KVs into spans, stores them in an offline index, and retrieves the relevant KVs into memory for various queries. Experimental results on popular long text benchmarks show that Ltri-LLM can achieve performance close to FA while maintaining efficient, streaming-based inference.

Transformer based large language models have achieved tremendous success. However, the significant memory and computational costs incurred during the inference process make it challenging to deploy large models on resource-constrained devices. In this paper, we investigate compression and efficient inference methods for large language models from an algorithmic perspective. Regarding taxonomy, similar to smaller models, compression and acceleration algorithms for large language models can still be categorized into quantization, pruning, distillation, compact architecture design, dynamic networks. However, Large language models have two prominent characteristics compared to smaller models: (1) Most of compression algorithms require finetuning or even retraining the model after compression. The most notable aspect of large models is the very high cost associated with model finetuning or training. Therefore, many algorithms for large models, such as quantization and pruning, start to explore tuning-free algorithms. (2) Large models emphasize versatility and generalization rather than performance on a single task. Hence, many algorithms, such as knowledge distillation, focus on how to preserving their versatility and generalization after compression. Since these two characteristics were not very pronounced in early large models, we further distinguish large language models into medium models and ``real'' large models. Additionally, we also provide an introduction to some mature frameworks for efficient inference of large models, which can support basic compression or acceleration algorithms, greatly facilitating model deployment for users.

In enterprise settings, efficiently retrieving relevant information from large and complex knowledge bases is essential for operational productivity and informed decision-making. This research presents a systematic framework for metadata enrichment using large language models (LLMs) to enhance document retrieval in Retrieval-Augmented Generation (RAG) systems. Our approach employs a comprehensive, structured pipeline that dynamically generates meaningful metadata for document segments, substantially improving their semantic representations and retrieval accuracy. Through extensive experiments, we compare three chunking strategies-semantic, recursive, and naive-and evaluate their effectiveness when combined with advanced embedding techniques. The results demonstrate that metadata-enriched approaches consistently outperform content-only baselines, with recursive chunking paired with TF-IDF weighted embeddings yielding an 82.5% precision rate compared to 73.3% for semantic content-only approaches. The naive chunking strategy with prefix-fusion achieved the highest Hit Rate@10 of 0.925. Our evaluation employs cross-encoder reranking for ground truth generation, enabling rigorous assessment via Hit Rate and Metadata Consistency metrics. These findings confirm that metadata enrichment enhances vector clustering quality while reducing retrieval latency, making it a key optimization for RAG systems across knowledge domains. This work offers practical insights for deploying high-performance, scalable document retrieval solutions in enterprise settings, demonstrating that metadata enrichment is a powerful approach for enhancing RAG effectiveness.

We propose a simple neural architecture for natural language inference. Our approach uses attention to decompose the problem into subproblems that can be solved separately, thus making it trivially parallelizable. On the Stanford Natural Language Inference (SNLI) dataset, we obtain state-of-the-art results with almost an order of magnitude fewer parameters than previous work and without relying on any word-order information. Adding intra-sentence attention that takes a minimum amount of order into account yields further improvements.

Recent advancements in Large Language Model (LLM) compression, such as BitNet and BitNet b1.58, have marked significant strides in reducing the computational demands of LLMs through innovative one-bit quantization techniques. We extend this frontier by looking at Large Inference Models (LIMs) that have become indispensable across various applications. However, their scale and complexity often come at a significant computational cost. We introduce a novel approach that leverages one-bit algorithm unrolling, effectively integrating information from the physical world in the model architecture. Our method achieves a bit-per-link rate significantly lower than the 1.58 bits reported in prior work, thanks to the natural sparsity that emerges in our network architectures. We numerically demonstrate that the proposed one-bit algorithm unrolling scheme can improve both training and test outcomes by effortlessly increasing the number of layers while substantially compressing the network. Additionally, we provide theoretical results on the generalization gap, convergence rate, stability, and sensitivity of our proposed one-bit algorithm unrolling.

Neural document retrieval often treats a corpus as a flat cloud of vectors scored at a single granularity, leaving corpus structure underused and explanations opaque. We use Cobweb--a hierarchy-aware framework--to organize sentence embeddings into a prototype tree and rank documents via coarse-to-fine traversal. Internal nodes act as concept prototypes, providing multi-granular relevance signals and a transparent rationale through retrieval paths. We instantiate two inference approaches: a generalized best-first search and a lightweight path-sum ranker. We evaluate our approaches on MS MARCO and QQP with encoder (e.g., BERT/T5) and decoder (GPT-2) representations. Our results show that our retrieval approaches match the dot product search on strong encoder embeddings while remaining robust when kNN degrades: with GPT-2 vectors, dot product performance collapses whereas our approaches still retrieve relevant results. Overall, our experiments suggest that Cobweb provides competitive effectiveness, improved robustness to embedding quality, scalability, and interpretable retrieval via hierarchical prototypes.

Large Language Models (LLMs) face computational inefficiencies and redundant processing when handling long context inputs, prompting a focus on compression techniques. While existing semantic vector-based compression methods achieve promising performance, these methods fail to account for the intrinsic information density variations between context chunks, instead allocating soft tokens uniformly across context chunks. This uniform distribution inevitably diminishes allocation to information-critical regions. To address this, we propose Dynamic Allocation of Soft Tokens (DAST), a simple yet effective method that leverages the LLM's intrinsic understanding of contextual relevance to guide compression. DAST combines perplexity-based local information with attention-driven global information to dynamically allocate soft tokens to the informative-rich chunks, enabling effective, context-aware compression. Experimental results across multiple benchmarks demonstrate that DAST surpasses state-of-the-art methods.

We introduce a novel retrieval-augmented generation (RAG) framework tailored for multihop question answering. First, our system uses large language model (LLM) to decompose complex multihop questions into a sequence of single-hop subquestions that guide document retrieval. This decomposition mitigates the ambiguity inherent in multi-hop queries by clearly targeting distinct knowledge facets. Second, instead of embedding raw or chunked documents directly, we generate answerable questions from each document chunk using Qwen3-8B, embed these generated questions, and retrieve relevant chunks via question-question embedding similarity. During inference, the retrieved chunks are then fed along with the original question into the RAG pipeline. We evaluate on three multihop question datasets (MuSiQue, 2WikiMultiHopQa, HotpotQA) from LongBench. Our method improves RAG performacne compared to baseline systems. Our contributions highlight the benefits of using answerable-question embeddings for RAG, and the effectiveness of LLM-based query decomposition for multihop scenarios.

Large language models allocate uniform computation across all tokens, ignoring that some sequences are trivially predictable while others require deep reasoning. We introduce ConceptMoE, which dynamically merges semantically similar tokens into concept representations, performing implicit token-level compute allocation. A learnable chunk module identifies optimal boundaries by measuring inter-token similarity, compressing sequences by a target ratio R before they enter the compute-intensive concept model. Crucially, the MoE architecture enables controlled evaluation: we reallocate saved computation to match baseline activated FLOPs (excluding attention map computation) and total parameters, isolating genuine architectural benefits. Under these conditions, ConceptMoE consistently outperforms standard MoE across language and vision-language tasks, achieving +0.9 points on language pretraining, +2.3 points on long context understanding, and +0.6 points on multimodal benchmarks. When converting pretrained MoE during continual training with layer looping, gains reach +5.5 points, demonstrating practical applicability. Beyond performance, ConceptMoE reduces attention computation by up to R^2times and KV cache by Rtimes. At R=2, empirical measurements show prefill speedups reaching 175\% and decoding speedups up to 117\% on long sequences. The minimal architectural modifications enable straightforward integration into existing MoE, demonstrating that adaptive concept-level processing fundamentally improves both effectiveness and efficiency of large language models.

Tokenization efficiency plays a critical role in the performance and cost of large language models (LLMs), yet most models rely on static tokenizers optimized for general-purpose corpora. These tokenizers' fixed vocabularies often fail to adapt to domain- or language-specific inputs, leading to longer token sequences and higher computational costs. We introduce zip2zip, a framework that enables LLMs to dynamically adjust token vocabulary at inference time, allowing for fewer generated tokens and thus faster inference. zip2zip consists of three key components: (1) a tokenizer based on Lempel-Ziv-Welch (LZW) compression that incrementally compresses tokens into reusable "hypertokens" on the fly; (2) an embedding layer that computes embeddings for newly formed hypertokens at runtime; and (3) a causal language modeling variant that trains the model to operate on hypertokenized, compressed sequences. We show that an existing LLM can be zip2zip-fied in 10 GPU-hours via parameter-efficient finetuning. The resulting zip2zip LLMs effectively learn to use hypertokens at inference time, reducing input and output sequence length by 20-60\%, with significant improvements in inference latency.

We introduce Chunk-Distilled Language Modeling (CD-LM), an approach to text generation that addresses two challenges in current large language models (LLMs): the inefficiency of token-level generation, and the difficulty of adapting to new data and knowledge. Our method combines deep network-based LLMs with a straightforward retrieval module, which allows the generation of multi-token text chunks at a single decoding step. Our retrieval framework enables flexible construction of model- or domain-specific datastores, either leveraging the internal knowledge of existing models, or incorporating expert insights from human-annotated corpora. This adaptability allows for enhanced control over the language model's distribution without necessitating additional training. We present the CD-LM formulation along with performance metrics demonstrating its ability to improve language model performance and efficiency across a diverse set of downstream tasks. Code and data will be made publicly available.

Despite incredible progress in language models (LMs) in recent years, largely resulting from moving away from specialized models designed for specific tasks to general models based on powerful architectures (e.g. the Transformer) that learn everything from raw data, pre-processing steps such as tokenization remain a barrier to true end-to-end foundation models. We introduce a collection of new techniques that enable a dynamic chunking mechanism which automatically learns content -- and context -- dependent segmentation strategies learned jointly with the rest of the model. Incorporating this into an explicit hierarchical network (H-Net) allows replacing the (implicitly hierarchical) tokenization-LM-detokenization pipeline with a single model learned fully end-to-end. When compute- and data- matched, an H-Net with one stage of hierarchy operating at the byte level outperforms a strong Transformer language model operating over BPE tokens. Iterating the hierarchy to multiple stages further increases its performance by modeling multiple levels of abstraction, demonstrating significantly better scaling with data and matching a token-based Transformer of twice its size. H-Nets pretrained on English show significantly increased character-level robustness, and qualitatively learn meaningful data-dependent chunking strategies without any heuristics or explicit supervision. Finally, the H-Net's improvement over tokenized pipelines is further increased in languages and modalities with weaker tokenization heuristics, such as Chinese and code, or DNA sequences (nearly 4x improvement in data efficiency over baselines), showing the potential of true end-to-end models that learn and scale better from unprocessed data.

The effectiveness of Retrieval-Augmented Generation (RAG) is highly dependent on how documents are chunked, that is, segmented into smaller units for indexing and retrieval. Yet, commonly used "one-size-fits-all" approaches often fail to capture the nuanced structure and semantics of diverse texts. Despite its central role, chunking lacks a dedicated evaluation framework, making it difficult to assess and compare strategies independently of downstream performance. We challenge this paradigm by introducing Adaptive Chunking, a framework that selects the most suitable chunking strategy for each document based on a set of five novel intrinsic, document-based metrics: References Completeness (RC), Intrachunk Cohesion (ICC), Document Contextual Coherence (DCC), Block Integrity (BI), and Size Compliance (SC), which directly assess chunking quality across key dimensions. To support this framework, we also introduce two new chunkers, an LLM-regex splitter and a split-then-merge recursive splitter, alongside targeted post-processing techniques. On a diverse corpus spanning legal, technical, and social science domains, our metric-guided adaptive method significantly improves downstream RAG performance. Without changing models or prompts, our framework increases RAG outcomes, raising answers correctness to 72% (from 62-64%) and increasing the number of successfully answered questions by over 30% (65 vs. 49). These results demonstrate that adaptive, document-aware chunking, guided by a complementary suite of intrinsic metrics, offers a practical and effective path to more robust RAG systems. Code available at https://github.com/ekimetrics/adaptive-chunking.

When completing knowledge-intensive tasks, humans sometimes need not just an answer but also a corresponding reference passage for auxiliary reading. Previous methods required obtaining pre-segmented article chunks through additional retrieval models. This paper explores leveraging the parameterized knowledge stored during the pre-training phase of large language models (LLMs) to independently recall reference passage from any starting position. We propose a two-stage framework that simulates the scenario of humans recalling easily forgotten references. Initially, the LLM is prompted to recall document title identifiers to obtain a coarse-grained document set. Then, based on the acquired coarse-grained document set, it recalls fine-grained passage. In the two-stage recall process, we use constrained decoding to ensure that content outside of the stored documents is not generated. To increase speed, we only recall a short prefix in the second stage, then locate its position to retrieve a complete passage. Experiments on KILT knowledge-sensitive tasks have verified that LLMs can independently recall reference passage location in various task forms, and the obtained reference significantly assist downstream tasks.

Large Language Models (LLMs) have exhibited exceptional performance across a spectrum of natural language processing tasks. However, their substantial sizes pose considerable challenges, particularly in computational demands and inference speed, due to their quadratic complexity. In this work, we have identified a key pattern: certain seemingly meaningless special tokens (i.e., separators) contribute disproportionately to attention scores compared to semantically meaningful tokens. This observation suggests that information of the segments between these separator tokens can be effectively condensed into the separator tokens themselves without significant information loss. Guided by this insight, we introduce SepLLM, a plug-and-play framework that accelerates inference by compressing these segments and eliminating redundant tokens. Additionally, we implement efficient kernels for training acceleration. Experimental results across training-free, training-from-scratch, and post-training settings demonstrate SepLLM's effectiveness. Notably, using the Llama-3-8B backbone, SepLLM achieves over 50% reduction in KV cache on the GSM8K-CoT benchmark while maintaining comparable performance. Furthermore, in streaming settings, SepLLM effectively processes sequences of up to 4 million tokens or more while maintaining consistent language modeling capabilities.

Long context fine-tuning of large language models(LLMs) involves training on datasets that are predominantly composed of short sequences and a small proportion of longer sequences. However, existing approaches overlook this long-tail distribution and employ training strategies designed specifically for long sequences. Moreover, these approaches also fail to address the challenges posed by variable sequence lengths during distributed training, such as load imbalance in data parallelism and severe pipeline bubbles in pipeline parallelism. These issues lead to suboptimal training performance and poor GPU resource utilization. To tackle these problems, we propose a chunk-centric training method named ChunkFlow. ChunkFlow reorganizes input sequences into uniformly sized chunks by consolidating short sequences and splitting longer ones. This approach achieves optimal computational efficiency and balance among training inputs. Additionally, ChunkFlow incorporates a state-aware chunk scheduling mechanism to ensure that the peak memory usage during training is primarily determined by the chunk size rather than the maximum sequence length in the dataset. Integrating this scheduling mechanism with existing pipeline scheduling algorithms further enhances the performance of distributed training. Experimental results demonstrate that, compared with Megatron-LM, ChunkFlow can be up to 4.53x faster in the long context fine-tuning of LLMs. Furthermore, we believe that ChunkFlow serves as an effective solution for a broader range of scenarios, such as long context continual pre-training, where datasets contain variable-length sequences.

Accelerating inference in Large Language Models (LLMs) is critical for real-time interactions, as they have been widely incorporated into real-world services. Speculative decoding, a fully algorithmic solution, has gained attention for improving inference speed by drafting and verifying tokens, thereby generating multiple tokens in a single forward pass. However, current drafting strategies usually require significant fine-tuning or have inconsistent performance across tasks. To address these challenges, we propose Hierarchy Drafting (HD), a novel lossless drafting approach that organizes various token sources into multiple databases in a hierarchical framework based on temporal locality. In the drafting step, HD sequentially accesses multiple databases to obtain draft tokens from the highest to the lowest locality, ensuring consistent acceleration across diverse tasks and minimizing drafting latency. Our experiments on Spec-Bench using LLMs with 7B and 13B parameters demonstrate that HD outperforms existing database drafting methods, achieving robust inference speedups across model sizes, tasks, and temperatures.

The rapid growth in the parameters of large language models (LLMs) has made inference latency a fundamental bottleneck, limiting broader application of LLMs. Speculative decoding represents a lossless approach to accelerate inference through a guess-and-verify paradigm, leveraging the parallel capabilities of modern hardware. Some speculative decoding methods rely on additional structures to guess draft tokens, such as small models or parameter-efficient architectures, which need extra training before use. Alternatively, retrieval-based train-free techniques build libraries from pre-existing corpora or by n-gram generation. However, they face challenges like large storage requirements, time-consuming retrieval, and limited adaptability. Observing that candidate tokens generated during the decoding process are likely to reoccur in future sequences, we propose Token Recycling. This approach stores candidate tokens in an adjacency matrix and employs a breadth-first search (BFS)-like algorithm on the matrix to construct a draft tree. The tree is then validated through tree attention. New candidate tokens from the decoding process are then used to update the matrix. Token Recycling requires \textless2MB of additional storage and achieves approximately 2x speedup across all sizes of LLMs. It significantly outperforms existing train-free methods by 30\% and even a training method by 25\%. It can be directly applied to any existing LLMs and tasks without the need for adaptation.

Despite the remarkable strides made by autoregressive language models, their potential is often hampered by the slow inference speeds inherent in sequential token generation. Blockwise parallel decoding (BPD) was proposed by Stern et al. (2018) as a way to improve inference speed of language models. In this paper, we make two contributions to understanding and improving BPD drafts. We first offer an analysis of the token distributions produced by the BPD prediction heads. Secondly, we use this analysis to inform algorithms to improve BPD inference speed by refining the BPD drafts using small n-gram or neural language models. We empirically show that these refined BPD drafts yield a higher average verified prefix length across tasks.

Diffusion Large Language Models (dLLMs) offer a compelling paradigm for natural language generation, leveraging parallel decoding and bidirectional attention to achieve superior global coherence compared to autoregressive models. While recent works have accelerated inference via KV cache reuse or heuristic decoding, they overlook the intrinsic inefficiencies within the block-wise diffusion process. Specifically, they suffer from spatial redundancy by modeling informative-sparse suffix regions uniformly and temporal inefficiency by applying fixed denoising schedules across all the decoding process. To address this, we propose Streaming-dLLM, a training-free framework that streamlines inference across both spatial and temporal dimensions. Spatially, we introduce attenuation guided suffix modeling to approximate the full context by pruning redundant mask tokens. Temporally, we employ a dynamic confidence aware strategy with an early exit mechanism, allowing the model to skip unnecessary iterations for converged tokens. Extensive experiments show that Streaming-dLLM achieves up to 68.2X speedup while maintaining generation quality, highlighting its effectiveness in diffusion decoding. The code is available at https://github.com/xiaoshideta/Streaming-dLLM.

Retrieval-Augmented Generation (RAG) systems are increasingly vital for navigating the ever-expanding body of scientific literature, particularly in high-stakes domains such as chemistry. Despite the promise of RAG, foundational design choices -- such as how documents are segmented and represented -- remain underexplored in domain-specific contexts. This study presents the first large-scale, systematic evaluation of chunking strategies and embedding models tailored to chemistry-focused RAG systems. We investigate 25 chunking configurations across five method families and evaluate 48 embedding models on three chemistry-specific benchmarks, including the newly introduced QuestChemRetrieval dataset. Our results reveal that recursive token-based chunking (specifically R100-0) consistently outperforms other approaches, offering strong performance with minimal resource overhead. We also find that retrieval-optimized embeddings -- such as Nomic and Intfloat E5 variants -- substantially outperform domain-specialized models like SciBERT. By releasing our datasets, evaluation framework, and empirical benchmarks, we provide actionable guidelines for building effective and efficient chemistry-aware RAG systems.

Existing benchmarks for context-aware chunk retrieval rely heavily on repurposed task items and rarely demonstrate that their queries genuinely require context, making score interpretation difficult. We focus on a specific kind of context dependence, legal cross-references, and introduce CRAwLeR, an operationalization of a narrow, well-defined phenomenon: cross-reference-aware context utilization for chunk retrieval in legal documents. Our pipeline detects legal cross-references, identifies query candidates, links target chunks to their relevant context, generates context-demanding queries with an LLM, and filters them through both an adversarial non-contextual baseline and an assurance prompt. We release CRAwLeR-DK and CRAwLeR-PL, Danish and Polish datasets built with this pipeline, alongside a strong Anthropic-style contextualization baseline. Manual analysis finds that approximately 80% of randomly sampled queries genuinely target the labelled target chunk and require context, with failures following systematic and named patterns. The benchmarks are hard but not solved: best Recall@10 reaches 55% on CRAwLeR-DK and 59% on CRAwLeR-PL. Ablation and failure analysis attribute the remaining gap to the contextualising LLM, not the retriever. Even when the target is retrieved in the top ten, labelled context chunks routinely outrank it. We are the first dataset for context-aware chunk retrieval to carefully consider construct validity and inspect our results in the light of such a narrow, well-defined phenomenon.

We present Inferflow, an efficient and highly configurable inference engine for large language models (LLMs). With Inferflow, users can serve most of the common transformer models by simply modifying some lines in corresponding configuration files, without writing a single line of source code. Compared with most existing inference engines, Inferflow has some key features. First, by implementing a modular framework of atomic build-blocks and technologies, Inferflow is compositionally generalizable to new models. Second, 3.5-bit quantization is introduced in Inferflow as a tradeoff between 3-bit and 4-bit quantization. Third, hybrid model partitioning for multi-GPU inference is introduced in Inferflow to better balance inference speed and throughput than the existing partition-by-layer and partition-by-tensor strategies.

Large language models are increasingly applied to multi-document and long-form inputs, yet long-context inference remains memory- and noise-inefficient. Key-value (KV) caching scales linearly with context length, while external retrieval methods often return lexically similar but causally irrelevant passages. We present S3-Attention, a memory-first inference-time framework that treats long-context processing as attention-aligned endogenous retrieval. S3-Attention decodes transient key and query projections into top-k sparse feature identifiers using lightweight sparse autoencoders, and constructs a CPU-based inverted index mapping features to token positions or spans during a single streaming scan. This design allows the KV cache to be discarded entirely and bounds GPU memory usage by the scan chunk size. At generation time, feature co-activation is used to retrieve compact evidence spans, optionally fused with BM25 for exact lexical matching. Under a unified LongBench evaluation protocol with fixed prompting, decoding, and matched token budgets, S3-Hybrid closely matches full-context inference across multiple model families and improves robustness in several information-dense settings. We also report an engineering limitation of the current prototype, which incurs higher wall-clock latency than optimized full-KV baselines, motivating future kernel-level optimization.

This technical report presents the training methodology and evaluation results of the open-source dewey_en_beta embedding model. The increasing demand for retrieval-augmented generation (RAG) systems and the expanding context window capabilities of large language models (LLMs) have created critical challenges for conventional embedding models. Current approaches often struggle to maintain semantic coherence when processing documents exceeding typical sequence length limitations, significantly impacting retrieval performance in knowledge-intensive applications. This paper presents dewey_en_beta, a novel text embedding model that achieves excellent performance on MTEB (Eng, v2) and LongEmbed benchmark while supporting 128K token sequences. Our technical contribution centers on chunk alignment training, an innovative methodology that enables the simultaneous generation of localized chunk embeddings and global document-level representations through distillation. Information regarding the model release can be found at https://huggingface.co/infgrad/dewey_en_beta.

We propose new static word embeddings optimised for sentence semantic representation. We first extract word embeddings from a pre-trained Sentence Transformer, and improve them with sentence-level principal component analysis, followed by either knowledge distillation or contrastive learning. During inference, we represent sentences by simply averaging word embeddings, which requires little computational cost. We evaluate models on both monolingual and cross-lingual tasks and show that our model substantially outperforms existing static models on sentence semantic tasks, and even rivals a basic Sentence Transformer model (SimCSE) on some data sets. Lastly, we perform a variety of analyses and show that our method successfully removes word embedding components that are irrelevant to sentence semantics, and adjusts the vector norms based on the influence of words on sentence semantics.

Modern language models still rely on fixed, pre-defined subword tokenizations. Once a tokenizer is trained, the LM can only operate at this fixed level of granularity, which often leads to brittle and counterintuitive behaviors even in otherwise strong reasoning models. We introduce ByteFlow Net, a new hierarchical architecture that removes tokenizers entirely and instead enables models to learn their own segmentation of raw byte streams into semantically meaningful units. ByteFlow Net performs compression-driven segmentation based on the coding rate of latent representations, yielding adaptive boundaries while preserving a static computation graph via Top-K selection. Unlike prior self-tokenizing methods that depend on brittle heuristics with human-designed inductive biases, ByteFlow Net adapts its internal representation granularity to the input itself. Experiments demonstrate that this compression-based chunking strategy yields substantial performance gains, with ByteFlow Net outperforming both BPE-based Transformers and previous byte-level architectures. These results suggest that end-to-end, tokenizer-free modeling is not only feasible but also more effective, opening a path toward more adaptive and information-grounded language models.

Diffusion large language models (dLLMs) have emerged as a promising alternative for text generation, distinguished by their native support for parallel decoding. In practice, block inference is crucial for avoiding order misalignment in global bidirectional decoding and improving output quality. However, the widely-used fixed, predefined block (naive) schedule is agnostic to semantic difficulty, making it a suboptimal strategy for both quality and efficiency: it can force premature commitments to uncertain positions while delaying easy positions near block boundaries. In this work, we analyze the limitations of naive block scheduling and disclose the importance of dynamically adapting the schedule to semantic difficulty for reliable and efficient inference. Motivated by this, we propose Dynamic Sliding Block (DSB), a training-free block scheduling method that uses a sliding block with a dynamic size to overcome the rigidity of the naive block. To further improve efficiency, we introduce DSB Cache, a training-free KV-cache mechanism tailored to DSB. Extensive experiments across multiple models and benchmarks demonstrate that DSB, together with DSB Cache, consistently improves both generation quality and inference efficiency for dLLMs. Code is released at https://github.com/lizhuo-luo/DSB.

Unsupervised constituency parsers organize phrases within a sentence into a tree-shaped syntactic constituent structure that reflects the organization of sentence semantics. However, the traditional objective of maximizing sentence log-likelihood (LL) does not explicitly account for the close relationship between the constituent structure and the semantics, resulting in a weak correlation between LL values and parsing accuracy. In this paper, we introduce a novel objective for training unsupervised parsers: maximizing the information between constituent structures and sentence semantics (SemInfo). We introduce a bag-of-substrings model to represent the semantics and apply the probability-weighted information metric to estimate the SemInfo. Additionally, we develop a Tree Conditional Random Field (TreeCRF)-based model to apply the SemInfo maximization objective to Probabilistic Context-Free Grammar (PCFG) induction, the state-of-the-art method for unsupervised constituency parsing. Experiments demonstrate that SemInfo correlates more strongly with parsing accuracy than LL. Our algorithm significantly enhances parsing accuracy by an average of 7.85 points across five PCFG variants and in four languages, achieving new state-of-the-art results in three of the four languages.

Autoregressive language models generate text one token at a time, yet natural language is inherently structured in multi-token units, including phrases, n-grams, and collocations that carry meaning jointly. This one-token bottleneck limits both the expressiveness of the model during pre-training and its throughput at inference time. Existing remedies such as speculative decoding or diffusion-based language models either leave the underlying bottleneck intact or sacrifice the causal structure essential to language modeling. We propose BitLM, a language model that represents each token as a fixed-length binary code and employs a lightweight diffusion head to denoise multiple tokens in parallel within each block. Crucially, BitLM preserves left-to-right causal attention across blocks while making joint lexical decisions within each block, combining the reliability of autoregressive modeling with the parallelism of iterative refinement. By replacing the large-vocabulary softmax with bitwise denoising, BitLM reframes token generation as iterative commitment in a compact binary space, enabling more efficient pre-training and substantially faster inference without altering the causal foundation that makes language models effective. Our results demonstrate that the one-token-at-a-time paradigm is not a fundamental requirement but an interface choice, and that changing it can yield a stronger and faster language model. We hope BitLM points toward a promising direction for next-generation language model architectures.

Subword tokenization is an essential part of modern large language models (LLMs), yet its specific contributions to training efficiency and model performance remain poorly understood. In this work, we decouple the effects of subword tokenization by isolating them within a controlled byte-level pretraining pipeline. We formulate and test hypotheses across various dimensions, including sample throughput, vocabulary scaling, and the linguistic prior of subword boundaries. By simulating these effects in a byte-level setting, we refine our understanding of why subword models outperform raw byte models and offer insights to improve the pretraining of future byte-level and subword models. Specifically, our experiments highlight the critical role of increased training throughput and the integration of subword boundaries as either explicit priors or inductive biases.

Many modern NLP systems rely on word embeddings, previously trained in an unsupervised manner on large corpora, as base features. Efforts to obtain embeddings for larger chunks of text, such as sentences, have however not been so successful. Several attempts at learning unsupervised representations of sentences have not reached satisfactory enough performance to be widely adopted. In this paper, we show how universal sentence representations trained using the supervised data of the Stanford Natural Language Inference datasets can consistently outperform unsupervised methods like SkipThought vectors on a wide range of transfer tasks. Much like how computer vision uses ImageNet to obtain features, which can then be transferred to other tasks, our work tends to indicate the suitability of natural language inference for transfer learning to other NLP tasks. Our encoder is publicly available.

The exponential expansion of context windows in LLMs has unlocked capabilities for long-document understanding but introduced severe bottlenecks in inference latency and information utilization. Existing compression methods often suffer from high training costs or semantic fragmentation due to aggressive token pruning. In this paper, we propose BEAVER, a novel training-free framework that shifts compression from linear token removal to structure-aware hierarchical selection. BEAVER maximizes hardware parallelism by mapping variable-length contexts into dense page-level tensors via dual-path pooling, and preserves discourse integrity through a hybrid planner combining semantic and lexical dual-branch selection with sentence smoothing. Extensive evaluations on four long-context benchmarks demonstrate that BEAVER achieves comparable performance to state-of-the-art (SOTA) methods like LongLLMLingua. Notably, on the RULER benchmark, BEAVER maintains high fidelity in multi-needle retrieval where baselines deteriorate. Regarding efficiency, BEAVER reduces latency by 26.4x on 128k contexts, offering a scalable solution for high-throughput applications. Our code is available at https://cslikai.cn/BEAVER/.

We present Prompt Cache, an approach for accelerating inference for large language models (LLM) by reusing attention states across different LLM prompts. Many input prompts have overlapping text segments, such as system messages, prompt templates, and documents provided for context. Our key insight is that by precomputing and storing the attention states of these frequently occurring text segments on the inference server, we can efficiently reuse them when these segments appear in user prompts. Prompt Cache employs a schema to explicitly define such reusable text segments, called prompt modules. The schema ensures positional accuracy during attention state reuse and provides users with an interface to access cached states in their prompt. Using a prototype implementation, we evaluate Prompt Cache across several LLMs. We show that Prompt Cache significantly reduce latency in time-to-first-token, especially for longer prompts such as document-based question answering and recommendations. The improvements range from 8x for GPU-based inference to 60x for CPU-based inference, all while maintaining output accuracy and without the need for model parameter modifications.

Recent progress in Language Models (LMs) has dramatically advanced the field of natural language processing (NLP), excelling at tasks like text generation, summarization, and question answering. However, their inference remains computationally expensive and energy intensive, especially in settings with limited hardware, power, or bandwidth. This makes it difficult to deploy LMs in mobile, edge, or cost sensitive environments. To address these challenges, recent approaches have introduced multi LLM intelligent model selection strategies that dynamically allocate computational resources based on query complexity -- using lightweight models for simpler queries and escalating to larger models only when necessary. This survey explores two complementary strategies for efficient LLM inference: (i) routing, which selects the most suitable model based on the query, and (ii) cascading or hierarchical inference (HI), which escalates queries through a sequence of models until a confident response is found. Both approaches aim to reduce computation by using lightweight models for simpler tasks while offloading only when needed. We provide a comparative analysis of these techniques across key performance metrics, discuss benchmarking efforts, and outline open challenges. Finally, we outline future research directions to enable faster response times, adaptive model selection based on task complexity, and scalable deployment across heterogeneous environments, making LLM based systems more efficient and accessible for real world applications.

As Large Language Models (LLMs) have made significant advancements across various tasks, such as question answering, translation, text summarization, and dialogue systems, the need for accuracy in information becomes crucial, especially for serious financial products serving billions of users like Alipay. To address this, Alipay has developed a Retrieval-Augmented Generation (RAG) system that grounds LLMs on the most accurate and up-to-date information. However, for a real-world product serving millions of users, the inference speed of LLMs becomes a critical factor compared to a mere experimental model. Hence, this paper presents a generic framework for accelerating the inference process, resulting in a substantial increase in speed and cost reduction for our RAG system, with lossless generation accuracy. In the traditional inference process, each token is generated sequentially by the LLM, leading to a time consumption proportional to the number of generated tokens. To enhance this process, our framework, named lookahead, introduces a multi-branch strategy. Instead of generating a single token at a time, we propose a Trie-based Retrieval (TR) process that enables the generation of multiple branches simultaneously, each of which is a sequence of tokens. Subsequently, for each branch, a Verification and Accept (VA) process is performed to identify the longest correct sub-sequence as the final output. Our strategy offers two distinct advantages: (1) it guarantees absolute correctness of the output, avoiding any approximation algorithms, and (2) the worst-case performance of our approach is equivalent to the conventional process. We conduct extensive experiments to demonstrate the significant improvements achieved by applying our inference acceleration framework. Code is avaliable: https://github.com/alipay/PainlessInferenceAcceleration.

In recent times, the emergence of Large Language Models (LLMs) has resulted in increasingly larger model size, posing challenges for inference on low-resource devices. Prior approaches have explored offloading to facilitate low-memory inference but often suffer from efficiency due to I/O bottlenecks. To achieve low-latency LLMs inference on resource-constrained devices, we introduce HeteGen, a novel approach that presents a principled framework for heterogeneous parallel computing using CPUs and GPUs. Based on this framework, HeteGen further employs heterogeneous parallel computing and asynchronous overlap for LLMs to mitigate I/O bottlenecks. Our experiments demonstrate a substantial improvement in inference speed, surpassing state-of-the-art methods by over 317% at most.

Retrieval-augmented language models can better adapt to changes in world state and incorporate long-tail knowledge. However, most existing methods retrieve only short contiguous chunks from a retrieval corpus, limiting holistic understanding of the overall document context. We introduce the novel approach of recursively embedding, clustering, and summarizing chunks of text, constructing a tree with differing levels of summarization from the bottom up. At inference time, our RAPTOR model retrieves from this tree, integrating information across lengthy documents at different levels of abstraction. Controlled experiments show that retrieval with recursive summaries offers significant improvements over traditional retrieval-augmented LMs on several tasks. On question-answering tasks that involve complex, multi-step reasoning, we show state-of-the-art results; for example, by coupling RAPTOR retrieval with the use of GPT-4, we can improve the best performance on the QuALITY benchmark by 20% in absolute accuracy.

Recent advances with large language models (LLM) illustrate their diverse capabilities. We propose a novel algorithm, staged speculative decoding, to accelerate LLM inference in small-batch, on-device scenarios. We address the low arithmetic intensity of small-batch inference by improving upon previous work in speculative decoding. First, we restructure the speculative batch as a tree, which reduces generation costs and increases the expected tokens per batch. Second, we add a second stage of speculative decoding. Taken together, we reduce single-batch decoding latency by 3.16x with a 762M parameter GPT-2-L model while perfectly preserving output quality.

Recent dynamic tokenisation methods operate directly on bytes and pool their latent representations into patches. This bears similarities to computational models of word segmentation that determine lexical boundaries using spikes in an autoregressive model's prediction error. Inspired by this connection, we explore whether grouping predictable bytes - rather than pooling their representations - can yield a useful fixed subword vocabulary. We propose a new information-driven subword tokeniser, ByteSpan, that uses an external byte-level LM during training to identify contiguous predictable byte sequences and group them into subwords. Experiments show that ByteSpan yields efficient vocabularies with higher morphological alignment scores than BPE for English. Multilingual experiments show similar compression and R\'enyi efficiency for 25 languages.

Current large language models (LLMs) primarily utilize next-token prediction method for inference, which significantly impedes their processing speed. In this paper, we introduce a novel inference methodology termed next-sentence prediction, aiming at enhancing the inference efficiency of LLMs. We present Sentence Variational Autoencoder (SentenceVAE), which includes a Sentence Encoder to compress multiple tokens in a sentence into a single token, and a Sentence Decoder to reconstruct it. By integrating SentenceVAE into the input and output layers of LLMs, we develop Sentence-level LLMs (SLLMs) that employ a sentence-by-sentence inference method. In addition, the SentenceVAE module of SLLMs can maintain the integrity of the original semantic content by segmenting the context into sentences, thereby improving accuracy while boosting inference speed. Moreover, compared to previous LLMs, SLLMs process fewer tokens over equivalent context length, significantly reducing memory demands for self-attention computation and facilitating the handling of longer context. Extensive experiments on Wanjuan dataset have revealed that the proposed method can accelerate inference speed by 204~365%, reduce perplexity (PPL) to 46~75% of its original metric, and decrease memory overhead by 86~91% for the equivalent context length, compared to previous token-by-token methods.

Recently, large language models (LLMs) have demonstrated superior performance across various tasks by adhering to scaling laws, which significantly increase model size. However, the huge computation overhead during inference hinders the deployment in industrial applications. Many works leverage traditional compression approaches to boost model inference, but these always introduce additional training costs to restore the performance and the pruning results typically show noticeable performance drops compared to the original model when aiming for a specific level of acceleration. To address these issues, we propose a fine-grained token-wise pruning approach for the LLMs, which presents a learnable router to adaptively identify the less important tokens and skip them across model blocks to reduce computational cost during inference. To construct the router efficiently, we present a search-based sparsity scheduler for pruning sparsity allocation, a trainable router combined with our proposed four low-dimensional factors as input and three proposed losses. We conduct extensive experiments across different benchmarks on different LLMs to demonstrate the superiority of our method. Our approach achieves state-of-the-art (SOTA) pruning results, surpassing other existing pruning methods. For instance, our method outperforms BlockPruner and ShortGPT by approximately 10 points on both LLaMA2-7B and Qwen1.5-7B in accuracy retention at comparable token sparsity levels.

Test-Time Training (TTT) models context dependencies by adapting part of the model's weights (referred to as fast weights) during inference. This fast weight, akin to recurrent states in RNNs, stores temporary memories of past tokens in the current sequence. Existing TTT methods struggled to show effectiveness in handling long-context data, due to their inefficiency on modern GPUs. The TTT layers in many of these approaches operate with extremely low FLOPs utilization (often <5%) because they deliberately apply small online minibatch sizes (e.g., updating fast weights every 16 or 64 tokens). Moreover, a small minibatch implies fine-grained block-wise causal dependencies in the data, unsuitable for data beyond 1D ordered sequences, like sets or N-dimensional grids such as images or videos. In contrast, we pursue the opposite direction by using an extremely large chunk update, ranging from 2K to 1M tokens across tasks of varying modalities, which we refer to as Large Chunk Test-Time Training (LaCT). It improves hardware utilization by orders of magnitude, and more importantly, facilitates scaling of nonlinear state size (up to 40% of model parameters), hence substantially improving state capacity, all without requiring cumbersome and error-prone kernel implementations. It also allows easy integration of sophisticated optimizers, e.g. Muon for online updates. We validate our approach across diverse modalities and tasks, including novel view synthesis with image set, language models, and auto-regressive video diffusion. Our approach can scale up to 14B-parameter AR video diffusion model on sequences up to 56K tokens. In our longest sequence experiment, we perform novel view synthesis with 1 million context length. We hope this work will inspire and accelerate new research in the field of long-context modeling and test-time training. Website: https://tianyuanzhang.com/projects/ttt-done-right

Performing inference on hundreds of thousands of samples with large language models (LLMs) can be computationally and financially costly. We propose batch prompting, a simple alternative prompting approach that enables the LLM to run inference in batches, instead of one sample at a time. Our method reduces both token and time costs while retaining downstream performance. We theoretically demonstrate that under a few-shot in-context learning setting, the inference costs decrease almost inverse linearly with the number of samples in each batch. We extensively validate the effectiveness of batch prompting on ten datasets across commonsense QA, arithmetic reasoning, and NLI/NLU: batch prompting significantly~(up to 5times with six samples in batch) reduces the LLM (Codex) inference token and time costs while achieving better or comparable performance. Our analysis shows that the number of samples in each batch and the complexity of tasks affect its performance. Further, batch prompting can be applied across different LLMs and reasoning methods.

This paper aims to improve the performance of large language models by addressing the variable computational demands in inference steps, where some tokens require more computational resources than others. We present HARP, a simple modification to "off-the-shelf" Transformer forward pass. Drawing from hesitation and the framing effect in decision-making, HARP selectively applies additional computation when the model encounters uncertainty during token generation. Our method mimics human cognitive processes by pausing at difficult decision points and reframing inputs for a different perspective. Unlike other approaches, HARP is model-agnostic, training-free, and easy to implement. We thoroughly evaluate our method across various downstream tasks and model sizes, demonstrating performance improvements up to +5.16%. Notably, HARP achieves these gains while maintaining inference times twice faster than beam search. Simple and yet with significant gains, HARP offers a practical solution for enhancing the performance of Transformer-based language models with minimal computational impact.

Inference of Large Language Models (LLMs) across computer clusters has become a focal point of research in recent times, with many acceleration techniques taking inspiration from CPU speculative execution. These techniques reduce bottlenecks associated with memory bandwidth, but also increase end-to-end latency per inference run, requiring high speculation acceptance rates to improve performance. Combined with a variable rate of acceptance across tasks, speculative inference techniques can result in reduced performance. Additionally, pipeline-parallel designs require many user requests to maintain maximum utilization. As a remedy, we propose PipeInfer, a pipelined speculative acceleration technique to reduce inter-token latency and improve system utilization for single-request scenarios while also improving tolerance to low speculation acceptance rates and low-bandwidth interconnects. PipeInfer exhibits up to a 2.15times improvement in generation speed over standard speculative inference. PipeInfer achieves its improvement through Continuous Asynchronous Speculation and Early Inference Cancellation, the former improving latency and generation speed by running single-token inference simultaneously with several speculative runs, while the latter improves speed and latency by skipping the computation of invalidated runs, even in the middle of inference.

Long context inference presents challenges at the system level with increased compute and memory requirements, as well as from an accuracy perspective in being able to reason over long contexts. Recently, several methods have been proposed to compress the prompt to reduce the context length. However, there has been little work on comparing the different proposed methods across different tasks through a standardized analysis. This has led to conflicting results. To address this, here we perform a comprehensive characterization and evaluation of different prompt compression methods. In particular, we analyze extractive compression, summarization-based abstractive compression, and token pruning methods. Surprisingly, we find that extractive compression often outperforms all the other approaches, and enables up to 10x compression with minimal accuracy degradation. Interestingly, we also find that despite several recent claims, token pruning methods often lag behind extractive compression. We only found marginal improvements on summarization tasks.

Retrieval-augmented language models (LMs) have received much attention recently. However, typically the retriever is not trained jointly as a native component of the LM, but added to an already-pretrained LM, which limits the ability of the LM and the retriever to adapt to one another. In this work, we propose the Retrieval-Pretrained Transformer (RPT), an architecture and training procedure for jointly training a retrieval-augmented LM from scratch for the task of modeling long texts. Given a recently generated text chunk in a long document, the LM computes query representations, which are then used to retrieve earlier chunks in the document, located potentially tens of thousands of tokens before. Information from retrieved chunks is fused into the LM representations to predict the next target chunk. We train the retriever component with a semantic objective, where the goal is to retrieve chunks that increase the probability of the next chunk, according to a reference LM. We evaluate RPT on four long-range language modeling tasks, spanning books, code, and mathematical writing, and demonstrate that RPT improves retrieval quality and subsequently perplexity across the board compared to strong baselines.

Large language models (LLMs) have shown promising efficacy across various tasks, becoming powerful tools in numerous aspects of human life. However, Transformer-based LLMs suffer a performance degradation when modeling long-term contexts due to they discard some information to reduce computational overhead. In this work, we propose a simple yet effective method to enable LLMs to take a deep breath, encouraging them to summarize information contained within discrete text chunks. Specifically, we segment the text into multiple chunks and insert special token <SR> at the end of each chunk. We then modify the attention mask to integrate the chunk's information into the corresponding <SR> token. This facilitates LLMs to interpret information not only from historical individual tokens but also from the <SR> token, aggregating the chunk's semantic information. Experiments on language modeling and out-of-domain downstream tasks validate the superiority of our approach.

Tokenization is associated with many poorly understood shortcomings in language models (LMs), yet remains an important component for long sequence scaling purposes. This work studies how tokenization impacts model performance by analyzing and comparing the stochastic behavior of tokenized models with their byte-level, or token-free, counterparts. We discover that, even when the two models are statistically equivalent, their predictive distributions over the next byte can be substantially different, a phenomenon we term as "tokenization bias''. To fully characterize this phenomenon, we introduce the Byte-Token Representation Lemma, a framework that establishes a mapping between the learned token distribution and its equivalent byte-level distribution. From this result, we develop a next-byte sampling algorithm that eliminates tokenization bias without requiring further training or optimization. In other words, this enables zero-shot conversion of tokenized LMs into statistically equivalent token-free ones. We demonstrate its broad applicability with two use cases: fill-in-the-middle (FIM) tasks and model ensembles. In FIM tasks where input prompts may terminate mid-token, leading to out-of-distribution tokenization, our method mitigates performance degradation and achieves an approximately 18% improvement in FIM coding benchmarks, consistently outperforming the standard token healing fix. For model ensembles where each model employs a distinct vocabulary, our approach enables seamless integration, resulting in improved performance (up to 3.7%) over individual models across various standard baselines in reasoning, knowledge, and coding.

Large language models face significant computational and memory challenges when processing long contexts. During inference, efficient management of the key-value (KV) cache, which stores intermediate activations for autoregressive generation, is critical to reducing memory overhead and improving computational efficiency. Traditional token-level efficient KV caching methods overlook semantic information, treating tokens independently without considering their semantic relationships. Meanwhile, existing semantic-preserving KV cache management approaches often suffer from substantial memory usage and high time-to-first-token. To address these limitations, we propose SentenceKV, a novel sentence-level semantic KV caching approach designed to enhance inference efficiency while preserving semantic coherence. During prefilling, SentenceKV groups tokens based on sentence-level semantic similarity, compressing sentence representations into concise semantic vectors stored directly on the GPU, while individual KV pairs are offloaded to CPU. During decoding, SentenceKV generates tokens by selectively retrieving semantically relevant sentence-level KV entries, leveraging the semantic similarity between the prefilling-stage semantic vectors and decoding-stage queries. This ensures efficient and contextually accurate predictions, minimizing the loading of redundant or irrelevant data into GPU memory and significantly reducing memory overhead while maintaining stable inference latency, even for extremely long contexts. Extensive evaluations on benchmarks including PG-19, LongBench, and Needle-In-A-Haystack demonstrate that SentenceKV significantly outperforms state-of-the-art methods in both efficiency and memory usage, without compromising model accuracy.

Long-context inference enhances the reasoning capability of Large Language Models (LLMs), but incurs significant computational overhead. Token-oriented methods, such as pruning and skipping, have shown great promise in reducing inference latency, yet still suffer from inherently insufficient structure optimization, outdated selection criteria, and redundancy interference, resulting in suboptimal speed-accuracy trade-off. To address these issues, we propose a novel training-free framework dubbed Self-Predictive Token Skipping (SPTS), for efficient long-context LLM inference. Specifically, motivated by probing the influence of target layers prior to skipping, we design two selective token skipping strategies for typical structures, including Partial Attention Probing (PAP) for multi-head attention and Low-rank Transformation Probing (LTP) for feed forward network. The former selects informative tokens via partial forward attention computation, while the latter constructs a low-rank proxy network to predict token transformations. In addition, a Multi-Stage Delayed Pruning (MSDP) strategy reallocates skipping budgets and progressively removes redundant tokens across layers. Extensive experiments display the effectiveness of our method, achieving up to 2.46times and 2.29times speedups for prefilling and end-to-end generation, respectively, while maintaining state-of-the-art accuracy. We will release the source code upon acceptance.