KV-Cache Compression

Follow this topic Ask about this topic

Momentum

24 papers in the last four weeks, up 71% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 166

Jun 8, 2026cs.AI

From Rigid to Dynamic: Entropy-Guided Adaptive Inference for Long-Context LLMs

Existing sparse attention and KV cache compression methods for long-context LLM inference typically apply fixed sparsity patterns or uniform budgets across all attention heads, overlooking the substantial variation in attention behavior among heads and contexts. We observe two distinct entropy patterns among attention heads: Rigid Heads, whose entropy stays near zero across input segments, and Dynamic Heads, whose entropy fluctuates significantly. Crucially, the distribution of these types is context-dependent and cannot be predetermined offline. We therefore propose EntropyInfer, a training-free framework that uses attention entropy to adaptively allocate compute at the granularity of individual heads and segments during prefilling. For decoding, we introduce a latent KV cache compression scheme that leverages generated output tokens, rather than prefill tokens alone, to identify and retain the most critical cache entries. Extensive experiments on Llama, Qwen and openPangu model series show that EntropyInfer consistently outperforms baselines including SnapKV, AdaKV, and CritiPrefill, achieving up to 2.39

\times

end-to-end speedup beyond 100k tokens with minimal quality degradation compared to full attention. The code is released in https://github.com/SHA-4096/EntropyInfer.

Zhanchao Xu, Haoyang Li, Qingfa Xiao +4

Department of Computing, PolyU · DSA, HKUST(GZ) · CSE, HKUST

Long-Context Language Model Inference LLM Inference Acceleration Sparse Attention KV-Cache Compression

Jun 8, 2026cs.LG

FlashMemory-DeepSeek-V4: Lightning Index Ultra-Long Context via Lookahead Sparse Attention

Conventional LLMs keep the full KV cache loaded during decoding, causing a severe GPU memory bottleneck for ultra-long context serving. In this report, we propose Lookahead Sparse Attention (LSA), a novel inference paradigm powered by a Neural Memory Indexer built upon the DeepSeek-V4 architecture. Rather than passively attending to all historical tokens, LSA proactively predicts future context demands and preserves only the query-critical KV chunks in the GPU memory. Crucially, we instantiate this architecture via a backbone-free decoupled training strategy. By formulating the indexer as a standard dual-encoder architecture, we train it independently using standard retrieval training frameworks without ever loading the massive backbone model into GPU memory. We demonstrate that this "less is more" paradigm significantly maximizes serving efficiency while acting as an effective attention denoiser in tasks that rely on long-term global memory. Across primary long-context evaluation suites (e.g., LongBench-v2, LongMemEval, and RULER), FM-DS-V4 compresses the average physical KV cache footprint down to merely 13.5% of the full-context baseline, while consistently preserving or slightly elevating downstream accuracy (+0.6% absolute margin on average). Crucially, at extreme 500K scales, FlashMemory suppresses the physical KV cache overhead by over 90% without destabilizing the backbone's core reasoning capacities.

Yan Wang, Qifan Zhang, Jiachen Yu +12

Independent Researchers · Tencent · The Hong Kong University of Science and Technology (Guangzhou) +1

KV Caching Long-Context Language Model Inference Memory-Efficient Inference Sparse Attention KV-Cache Compression

Jun 7, 2026cs.LG

STAR-KV: Low-Rank KV Cache Compression via Soft Thresholding for Adaptive Rank Control

Low-rank projection has emerged as a promising approach for compressing the KV cache by exploiting hidden-dimension redundancy. However, prior methods rely on fixed or heuristic rank selection and struggle to achieve aggressive compression with minimal accuracy degradation. We propose STAR-KV, an adaptive low-rank KV cache compression framework with fine-grained rank control. STAR-KV encompasses 1) a differentiable thresholding mechanism that enables optimal rank selection at both attention-head and block levels, 2) a hybrid decomposition strategy that applies different low-rank factorizations according to the sensitivity of key and value projections, and 3) a low-rank-aware mixed precision quantization that leverages data statistics for near lossless low-bit quantization. Evaluated across multiple LLMs and benchmarks, STAR-KV achieves up to 75% KV cache compression and up to 20x overall KV cache reduction when combined with quantization. Enabled by custom Triton-based GPU kernels, STAR-KV delivers up to 6.9x speedup for the attention module and 3.1x end-to-end generation throughput. Our code is publicly available at: https://github.com/PriyanshBhatnagar/STAR-KV.

Priyansh Bhatnagar, Ashkan Moradifirouzabadi, Se-Hyun Yang +3

University of California San Diego, San Diego, CA, USA · Dnotitia Inc., Seoul, Republic of Korea · Hanyang University, Seoul, Republic of Korea

Mixed-Precision Quantization KV Caching Low-Rank Matrix Decomposition LLM Inference Acceleration Low-Rank Compression Low-Rank Approximation+1

Jun 6, 2026cs.CV

HACK++: Towards More Effective Head-Aware Key-Value Compression for Efficient Visual Autoregressive Modeling

Visual Autoregressive (VAR) models adopt a next-scale prediction paradigm, offering high-quality generation with substantially fewer decoding steps. However, existing VAR models suffer from significant attention complexity and severe memory overhead due to the accumulation of key-value (KV) caches across scales. In this paper, we tackle this challenge by introducing KV cache compression into the next-scale paradigm. We begin with an in-depth analysis of VAR attention and observe that attention heads can be stably divided into two functionally distinct categories: Contextual Heads focus on maintaining semantic consistency, while Structural Heads preserve spatial coherence. Their functional divergence makes existing one-size-fits-all compression methods perform poorly on VAR models. We further find that the two head types differ markedly in their reliance on historical scales, and that this reliance shifts across layers and generation steps, arguing for an adaptive cache budget allocation. To address these challenges, we propose HACK++, a training-free Head-Aware key-value Compression frameworK for VAR models. From a one-time offline calibration, HACK++ classifies head types and derives head-specific priors. At inference, it decouples attention from cache compression under independent budgets, bounding the current-scale attention cost while compressing the accumulated cache far more aggressively, via pattern-specific strategies and a reliance-aware budget allocation. Extensive experiments on multiple VAR models across text-to-image, class-conditional, and unified understanding-and-generation tasks validate the effectiveness and generalizability of HACK++. For example, on Infinity-2B/8B, HACK++ maintains near-lossless generation with only a 30% attention budget and a 10% cache budget, and remains robust even under a 1% cache budget.

Ziran Qin, Yuchen Jiang, Mingbao Lin +4

Shanghai Jiao Tong University, Shanghai, China · Rakuten, Singapore · Tsinghua University, Beijing, China

KV Caching Visual Autoregressive Models Autoregressive Image Generation KV-Cache Compression

Jun 6, 2026cs.LG

IntentKV: Cross-Turn Intent-Aware KV Cache Pruning for Agent Inference

Multi-turn LLM agents fan short queries into long trajectories of tool calls, search results, and intermediate reasoning. Both KV memory and KV read bandwidth grow by orders of magnitude across a single trajectory, making the key-value (KV) cache, not parameter compute, the dominant serving bottleneck for long-horizon agents. We introduce IntentKV, learned KV pruning that keeps the base LLM frozen. IntentKV maintains a session-level QueryMemory of cross-turn intent, scores live history tokens with a memory-attention rule, and adds a zero-initialized residual head with cross-attention over current-query K-vectors. To stay composable with prefix caches, eviction is a slot-map redirection: dropped positions route to a sentinel dead slot while surviving K/V rows, RoPE phases, and slot identities stay in place. IntentKV matches the no-pruning full-cache baseline with almost no accuracy drop under tight KV budgets: at an 8k KV budget, mean peak request tokens drop 23.9% on Qwen3-8B and 30.7% on Qwen2.5-14B. On the 100 longest BCP queries that all methods complete on Qwen2.5-14B, IntentKV-8k further cuts worst-case peak request tokens from 92.3k to 20.5k, a 77.8% reduction, and worst-case raw KV reads from 411M to 31M, a 92.6% reduction.

Junjie Li, Jiong Lou, Jie Li

Shanghai Jiao Tong University

KV Caching KV-Cache Management LLM Inference Acceleration KV-Cache Compression Long-Horizon LLM Agents KV-Cache Pruning

Jun 5, 2026cs.LG

Still: Amortized KV Cache Compaction in a Single Forward Pass

The KV cache is the memory bottleneck of long-horizon language model deployment. Practically, a deployable compactor must be lightweight enough to call during inference, expressive enough to preserve context under constraint, and reusable across a trajectory. Existing compaction methods satisfy only part of this requirement: selection methods are lightweight but subset-bound, while synthesis methods are expressive but rely on per-context optimization. Here we introduce Still, a small per-layer Perceiver trained once against a frozen base model that produces compact keys and values in a single forward pass. On Qwen and Gemma models, Still occupies the favorable side of the speed--quality frontier across compression ratios from

8\times

to

200\times

and context lengths from

8

k to

128

k. On the long-context RULER grid, Still exceeds the strongest baseline by 8--22 points. The same compact cache also supports free-form summarization, preserving most of the full-context gain on HELMET and winning a pairwise LongBench summarization comparison against KV-Distill. Because compaction is a forward pass, Still can be applied iteratively, entering a long-horizon regime unavailable to per-context methods. We show that amortization makes long-context cache compaction tractable, and synthesis makes its compact state useful at extreme compression.

Charles O'Neill, Alex Sandomirsky, Harry Partridge +2

Baseten San Francisco · Baseten London

KV Caching Long-Context Language Model Inference KV-Cache Management LLM Inference Acceleration KV-Cache Compression

Jun 5, 2026cs.DS

Towards Tight Bounds for Streaming Attention

The attention mechanism is a cornerstone of modern transformer architectures. However, its expressive power comes at the cost of quadratic runtime and linear space usage. In particular, the classical transformer architecture explicitly stores all previously seen input elements (tokens) in order to generate the next one. The problem of implementing a transformer in limited space, known as KV cache compression, has received much interest over the past few years, spurring the development of powerful heuristics. Recent works of Haris et al, COLT'25 and Kochetkova et al, NeurIPS'25, formalized KV cache compression as the streaming attention approximation problem, providing both upper bounds (based on discrepancy theory) and information theoretic lower bounds. However, those papers left open a significant gap between the upper and lower bounds. For example, the space usage of their algorithms increases with the precision parameter, but the lower bound does not get stronger. In this work, we revisit the streaming attention approximation problem and provide nearly tight bounds on its space complexity. On the algorithmic side, we achieve the result through a surprisingly tight interplay between three distinct methods for kernel density estimation: discrepancy-based coreset constructions (e.g., Charikar-Kapralov-Waingarten'24), the polynomial method (e.g., Greengard-Rokhlin'87, Alman-Song'23), and space partitioning (e.g., Andoni-Laarhoven-Razenshteyn-Waingarten'17, Charikar-Kapralov-Nouri-Siminelakis'20). On the lower bound side, our main technical contribution is a new technique for using the INDEX problem with a large amount of side information that we hope will prove useful in other high dimensional geometric estimation problems.

Justin Y. Chen, Ying Feng, Piotr Indyk +3

MIT · EPFL

Efficient Attention KV-Cache Compression Information-Theoretic Lower Bounds Streaming Algorithms

Jun 5, 2026cs.LG

Semantic Cache Distillation: Efficient State Transfer via Reuse and Selective Patching

Disaggregated serving alleviates memory bottlenecks in Large Language Model (LLM) inference but creates a severe communication bottleneck: transmitting high-dimensional Key-Value (KV) caches often dominates time-to-first-token (TTFT). Moreover, reusing caches across heterogeneous models (e.g., base and fine-tuned variants) causes semantic misalignment that accumulates over layers, degrading generation quality. We propose Semantic Cache Distillation (SCD), a loss-constrained framework that replaces raw KV transmission with compact semantic codes. SCD addresses these challenges via two mechanisms: (1) Reuse, which reconstructs most layers from low-rank subspaces to minimize transfer cost, and (2) Patch, which predicts normalized inputs at sparse transition layers to truncate error propagation. Empirically, SCD delivers up to 2.65

\times

TTFT speedup over the oracle consumer prefill and dominates quantization and selective recomputation baselines on the quality--latency Pareto frontier in bandwidth-constrained regimes, while keeping generation quality within 5% F1 of the oracle.

Qianli Ma, Zhiqing Tang, Hanshuai Cui +2

Faculty of Arts and Science, Beijing Normal University, Zhuhai 519087, China · Institute of Artificial Intelligence and Future Networks, Beijing Normal University, Zhuhai 519087, Guangdong, China · School of Artificial Intelligence, Beijing Normal University, Beijing 100875, China +1

LLM Serving KV Caching Disaggregated LLM Serving KV-Cache Management LLM Inference Acceleration KV-Cache Compression

Jun 4, 2026cs.LG

Tangram: Unlocking Non-Uniform KV Cache Compression for Efficient Multi-turn LLM Serving

Multi-turn LLM serving accumulates dialogue history whose Key-Value (KV) cache grows with every turn and every user, quickly exceeding the model weights themselves and making memory -- not compute -- the binding constraint on throughput. Non-uniform KV compression, which allocates heterogeneous budgets across attention heads, preserves accuracy far better than uniform schemes, yet remains impractical: modern serving stacks assume identical KV lengths across heads, so heterogeneity traps freed memory as page fragmentation, spends up to 25% of prefill time reclaiming scattered pages, and skews GPU workloads that inflate decode latency by up to

1.7\times

or burn 15--20% of each decode step on re-planning. We observe that this heterogeneity need not be discovered at runtime: head-wise retention follows a two-level structural regularity -- an input-invariant head ranking with narrowly bounded per-head ratios -- that can be calibrated offline from as few as 50 samples. Building on this insight, we present Tangram, a serving framework that statically resolves what prior systems handle dynamically: Budget Reservation fixes each head's post-compression footprint at scheduling time, eliminating page reclamation; Ragged Paging clusters similar-budget heads into independent page tables, turning fragmentation into reclaimable memory; and Ahead-of-Time Load Balancing precomputes balanced GPU partitions with zero runtime planning. Implemented on vLLM, Tangram serves as a drop-in substrate for existing non-uniform compression methods, matching their accuracy while improving end-to-end throughput by up to

2.6\times

over the full-KV baseline. Our implementation is publicly available at https://github.com/aiha-lab/TANGRAM.

Hyungmin Kim, Minsoo Kim, Hongseok Kim +1

LLM Serving KV Caching Memory-Efficient Optimization LLM Inference Acceleration KV-Cache Compression

Jun 4, 2026cs.AI

RedKnot: Efficient Long-Context LLM Serving with Head-Aware KV Reuse and SegPagedAttention

As the input length of large language model (LLM) serving continues to grow, the KV cache has become a dominant bottleneck in AI infrastructure. It limits GPU memory capacity, serving concurrency, cache reuse, and distributed scalability. Multiple important problems, including position-independent KV cache, prefix KV cache compression, hot/cold KV cache separation, and distributed KV cache management, all depend on how the KV cache is represented and managed. However, existing serving systems largely rely on a monolithic KV cache abstraction, where the KV cache is treated as a homogeneous sequence of token-level memory blocks and managed with similar policies across attention heads and serving scenarios. We observe that KV cache utility is highly structured across KV heads: different heads exhibit different functional roles, attention distances, and runtime importance. Therefore, a full KV cache is not always necessary for every head, token range, or serving scenario. We present RedKnot, a head-aware KV cache management system for LLM serving. RedKnot breaks the conventional monolithic KV cache abstraction by decomposing the KV cache along KV heads, whose importance and effective attention ranges vary significantly across serving scenarios. This head-level decomposition turns the KV cache from a monolithic tensor abstraction into a structured memory object, enabling RedKnot to uniformly support position-independent KV reuse, prefix KV compression, hot/cold KV separation, and distributed KV placement while preserving output fidelity and improving resource efficiency, without requiring model retraining or fine-tuning. RedKnot establishes a new foundation for AI infrastructure by transforming the KV cache from a monolithic, passive runtime artifact into a dynamic, model-aware runtime substrate for scalable LLM serving.

Yang Liu, ZhaoKai Luo, HuaYi Jin +5

†Xiaohongshu Inc., China · ¶Huawei Cloud · §Peking University

LLM Serving KV Caching KV-Cache Management KV-Cache Reuse KV-Cache Compression

Jun 4, 2026cs.CL

YouZhi: Towards High-Concurrency Financial LLMs via Adaptive GQA-to-MLA Transition

Large language models (LLMs) drive significant financial innovations, yet their high-concurrency deployment is severely bottlenecked by KV cache memory overhead, which inflates infrastructure costs and throttles scalability. To address this, we propose YouZhi-LLM, a highly efficient financial LLM empowered by a comprehensive structural transition and training pipeline natively built on the Huawei Ascend ecosystem. At its algorithmic core, YouZhi-LLM features a layer-adaptive GQA-to-MLA transition framework that dynamically assigns per-layer FreqFold sizes, maximizing KV-cache compression while minimizing perplexity degradation. To recover representation capacity and inject domain expertise, the Ascend-based training pipeline seamlessly integrates generalized knowledge distillation with financial-specific supervised fine-tuning. Evaluations demonstrate the superiority of this systematic approach, with the adaptive transition reducing perplexity degradation by up to 35% over uniform baselines. Crucially, when evaluated on Ascend NPUs via vLLM-Ascend, the massive KV-cache reduction translates directly into deployment efficiency. Compared to their respective base models, YouZhi-7B yields a 12.3% improvement in average financial benchmark score alongside a 2.69

\times

increase in maximum concurrency; similarly, YouZhi-14B achieves a 7.0% accuracy gain and a 2.43

\times

concurrency boost, establishing a new paradigm for cost-effective, high-throughput financial inference.

PSBC LLM Team, Huawei LLM Team, Ruihan Long +56

LLM Compression LLM Inference Acceleration Language Modeling KV-Cache Compression

Jun 3, 2026cs.CL

Cartridges at Scale: Training Modular KV Caches over Large Document Collections

Large Language Models can reason over long contexts, yet prefilling millions of tokens is wasteful as much of the content remains static across queries. Cartridges address this by distilling document collections into reusable key-value (KV) caches that eliminate prefilling while preserving accuracy. A critical limitation of this approach is that cartridges are monolithic and non-compositional: encoding an entire collection into a single KV block does not scale, and naively mixing cartridges trained in isolation collapses performance to near chance. We introduce Cartridges at Scale (CAS), a training framework for scalable multi-cartridge learning with dynamic distractor mixing and a memory-efficient budget manager that rotates hundreds of per-document cartridges between GPU and persistent storage. Our approach scales to collections exceeding a million tokens, improving over a monolithic cartridge by 10-31 points at comparable token budgets. Oracle cartridge accuracy falls within 2-6 points of full in-context learning even at high compression. When paired with retrieval for cartridge selection, CAS matches or exceeds conventional RAG accuracy while consuming 3-4x fewer prompt tokens.

Momchil Hardalov, Gonzalo Iglesias, Adrià de Gispert

Amazon AGI

Memory-Augmented Language Models KV Caching LLM Inference Acceleration KV-Cache Compression

Jun 2, 2026cs.LG

Value-Aware Stochastic KV Cache Eviction for Reasoning Models

Reasoning models improve accuracy through extended chains of thought, but their long outputs create a memory and compute bottleneck. KV cache eviction methods reduce this cost by evicting unimportant key-value pairs from the cache, yet they often yield worse accuracy than selection-based sparse attention alternatives, which keep the full KV cache. We identify key factors crucial to KV cache eviction accuracy. First, a small fraction of value states have abnormally large magnitudes, and evicting them causes catastrophic failure where models enter repetitive reasoning loops. Second, introducing stochasticity during eviction improves accuracy by increasing cache diversity. Based on these findings, we propose Value-aware Stochastic KV Cache Eviction (VaSE), a training-free recipe that protects large-magnitude value states and promotes diverse eviction decisions. Across six reasoning tasks, Qwen3 models using VaSE with 4x KV cache compression yield higher average accuracies than SOTA selection method at the same sparsity, while outperforming the strongest eviction method by more than 4%. Overall, VaSE bridges the gap between efficiency and accuracy, supporting FlashAttention2 and enabling a static memory footprint for reasoning models.

Ting-Yun Chang, Harvey Yiyun Fu, Deqing Fu +3

University of Southern California · University of Chicago

LLM Inference Efficiency KV Caching Memory-Efficient Optimization KV-Cache Eviction KV-Cache Compression Large Reasoning Models

Jun 1, 2026cs.CV

STaR-KV: Spatio-Temporal Adaptive Re-weighting for KV Cache Compression in GUI Vision-Language Models

Vision-language-model-based graphical user interface (GUI) agents have shown broad automation capabilities, yet deployment is bottlenecked by a key-value (KV) cache that grows linearly with interaction steps. For instance, UI-TARS-1.5-7B consumes 76 GB of GPU memory on merely five screenshots, approaching the capacity of mainstream 80 GB accelerators. Existing KV compression methods share two structural assumptions: aggregating visual-token importance into a single shared saliency map, and applying a fixed top-B cutoff to the fused score distribution. Pilot measurements refute both: spatial specialization lives at the attention-subspace level and migrates across layers, while the score distribution drifts in shape along a trajectory. We propose STaR-KV (Spatio-Temporal Adaptive Re-weighting), a training-free KV cache compression framework that calibrates token importance along three axes: (i) subspace-aware scoring driven by online spatial mutual information; (ii) a temporal stability discount that suppresses redundant cache entries from persistently attended subspaces; and (iii) an entropy-derived temperature that adaptively reshapes the score distribution. Across four GUI benchmarks, STaR-KV achieves the strongest average accuracy among state-of-the-art KV compression methods (e.g., GUIKV, SnapKV) at matched budgets, with no compression-stage FLOPs overhead (-0.07%) and cutting peak GPU memory by nearly 40% at a 20% KV-cache budget. Code is available at https://github.com/kawhiiiileo/STaR-KV.

Yuhang Han, Wenzheng Yang, Yujie Chen +4

1EPIC Lab, SJTU · 2HKUST (GZ) · 3The University of Sydney +3

Vision-Language Models KV Caching KV-Cache Compression GUI Automation

Jun 1, 2026cs.LG

MomentKV: Closing the Directional Gap in KV Cache Eviction for Long-Context Inference

Autoregressive decoding in Transformer-based language models relies on the KV cache, whose memory footprint grows linearly with sequence length and becomes the primary bottleneck for long-context inference. KV cache eviction addresses this by retaining a fixed-size subset of key-value pairs and discarding the rest. We identify that a primary source of output degradation is not the residual attention mass on evicted tokens, which existing methods already minimize, but a directional mismatch between the retained and evicted token sets. Specifically, the evicted tokens in practice are often near-orthogonal to the retained ones. Thus, even a small evicted mass could have an oversized impact on the resulting direction distribution and amplify into substantial output error. This reveals a fundamental limit in existing strategies. To address this, we propose MomentKV, which maintains compact, small-size moment statistics over the evicted token set, including a count, key mean, value mean, and value-key covariance. During eviction, the moment statistics is leveraged to identify tokens already well aligned with and captured by the accumulated summary, keeping the evicted set geometrically regular. During inference, they yield a closed-form first-order approximation of the evicted attention output, forming a mutually reinforcing loop between selective eviction and accurate correction. On LongBench and RULER with LLaMA-3.1-8B-Instruct and Qwen3-4B-Instruct, MomentKV outperforms all baselines at every cache budget, with the largest gains under aggressive compression.

Yu Li, Binxu Li, Tian Lan

George Washington University · Princeton University

KV Caching Long-Context Language Model Inference KV-Cache Eviction Transformer Attention KV-Cache Compression

May 30, 2026cs.CL

WaveFilter: Enhancing the Long-Context Capability of Diffusion LLMs via Wavelet-Guided KV Cache Filtering

Diffusion Large Language Models (DLMs) have demonstrated significant advantages across various tasks. However, constrained by their multi-step iterative inference mechanism, their computational overhead and inference latency in long-context tasks have become core bottlenecks restricting their large-scale deployment. When processing long sequences, existing Key-Value (KV) caching mechanisms often face a dilemma where generation quality degrades drastically, where the core challenge lies in precisely and efficiently filtering critical tokens within ultra-long contexts. Inspired by the human reading process, we propose \textbf{WaveFilter}, a universal and training-free caching framework. This framework innovatively introduces the wavelet transform for decomposition of long sequences to achieve precise identification of key tokens, based on which a sparse KV Cache is constructed to compute the final contextual representation. Experimental results demonstrate that WaveFilter, as a plug-and-play generic framework, significantly enhances the performance of existing mainstream KV Cache methods in complex long-context tasks.

Jinnan Yang, Yan Wang, Zhen Bi +5

Nanjing University of Science and Technology · Alibaba Group · Huzhou Normal University +1

Long-Context Language Model Inference Diffusion Language Model Inference Diffusion Model Caching KV-Cache Compression Diffusion Language Models

May 29, 2026cs.CV

Linear Scaling Video VLMs for Long Video Understanding

Video vision-language models (VLMs) are increasingly used in long-horizon and streaming settings, yet most video encoders still rely on spatiotemporal self-attention, causing compute and latency to grow quadratically with the number of frames. Existing efficiency methods improve scalability but often lose accuracy relative to full self-attention, for example through aggressive frame/token dropping or coarse attention approximations. We introduce StateKV, an inference-time method that adapts pretrained long-video VLMs to linear-time video prefill by carrying cross-frame context in a fixed-capacity, importance-based recurrent state, paired with a second full per-frame cache used for decoding. Across three long-video benchmarks and seven models spanning three families and multiple scales, StateKV remains close to full self-attention and consistently outperforms dominant sliding-window / recency-based streaming approximations, without fine-tuning or architectural changes. StateKV also reduces video-prefill cost measured FLOPs, enabling stronger accuracy at a fixed compute budget by running larger models. These results suggest a practical step toward scalable long-video understanding.

Cristobal Eyzaguirre, Jiajun Wu, Juan Carlos Niebles

Stanford University

Streaming Video Understanding Efficient VLM Inference Long-Video Understanding KV-Cache Compression

May 29, 2026cs.CL

GRKV: Global Regression for Training-Free KV Cache Compression in Long-Context LLMs

Large language models (LLMs) with extended context lengths rely on the key-value (KV) cache to support attention over prior tokens. However, maintaining the KV cache incurs substantial memory overhead, motivating KV-cache compression methods that enforce a fixed budget through eviction and merging. Modern eviction methods increasingly adopt span-based retention because preserving contiguous spans is empirically effective and better preserves semantic coherence. Yet, when combined with post-eviction merging, span-based retention concentrates merges onto a small set of span-boundary carrier tokens, producing a highly imbalanced merge pattern that exacerbates over-merging and increases information loss. To address this imbalance, we propose GRKV (Global Regression for KV Cache), a training-free KV-cache merging method that directly minimizes the discrepancy between compressed-cache and full-cache attention outputs. GRKV uses ridge-regression-based merge steps to distribute information from evicted tokens across retained tokens, while regularizing the updates to prevent over-smoothing. Across the LongBench and RULER long-context benchmarks, GRKV is the only merging method that improves overall performance with minimal overhead. Our code is available at https://github.com/pjunjie/GRKV.

Junjie Peng, You Wu, Haoyi Wu +4

1Sun Yat-sen University · 2ShanghaiTech University · 3Guangdong Province Key Laboratory of Information Security Technology

KV Caching Long-Context Language Modeling KV-Cache Compression Ridge Regression

May 28, 2026cs.CL

Probing the Prompt KV Cache: Where It Becomes Dispensable

Prior KV cache compression schemes empirically demonstrate that the prompt cache is partially redundant during decoding, dropping or summarising entries with little accuracy loss. We ask when and what kind of redundancy: at which layers, after how many decoding steps, and in what form can the prompt span KV cache be replaced without breaking the task. A controlled splice intervention swept over layer cutoff and decoding steps shows this redundancy is about form (chat template scaffolding) rather than content. Replacing the upper layer prompt span KV cache with KV cache from a chat template scaffold whose user content is a neutral filler recovers near clean accuracy, while zeroing the same slots collapses accuracy. The dissociation replicates across the Qwen3, Gemma 3, and Llama 3 families on multiple datasets.

Vinayshekhar Bannihatti Kumar, Manoj Ghuhan Arivazhagan, Disha Makhija +1

AWS AI Labs

KV Caching KV-Cache Management KV-Cache Compression Causal Interventions in Language Models Language Model Probing

May 28, 2026cs.CV

Future Forcing: Future-aware Training-free KV Cache Policy for Autoregressive Video Generation

Autoregressive (AR) video generation has emerged as a promising paradigm for long-horizon video synthesis, where each frame is generated conditioned on previously generated tokens. To accelerate inference, the KV cache is used to avoid redundant recomputation across generation steps. Nevertheless, its growth with generation length introduces increasing memory and error accumulation, limiting the scalability of AR models to even longer sequences. Existing KV cache compression methods mitigate this issue by selectively retaining only video tokens deemed important. However, most existing methods assess token importance using short-horizon signals derived from the current or historical generation context, making these methods prone to overlooking tokens that appear unimportant at early steps but later become critical for future frames. In this work, we identify an important property of trained AR video models: although RoPE-modulated queries evolve across autoregressive steps, the underlying canonical pre-RoPE query distribution remains remarkably stable throughout the video generation process. This approximate stationarity implies that future query distributions are estimable from historical statistics, enabling principled future-aware cache decisions without any additional training. Building on this insight, we propose Future Forcing, a training-free future-aware KV cache policy for AR video generation. Specifically, Future Forcing first constructs a future query proxy from historical statistics, then scores KV cache tokens by their importance under this proxy, and finally merges redundant token pairs within the affine subspace induced by the future query. Extensive experiments show that Future Forcing improves long-horizon consistency under limited KV caches, achieving up to 1.49 improvement in subject consistency on VBench-Long for 60s generation over existing AR video KV cache policies.

Jiayi Luo, Qiyan Liu, Tengyang Wang +8

BUAA · ZGCA · PKU +3

KV Caching Long-Horizon Video Generation KV-Cache Compression Autoregressive Video Generation Temporal Consistency in Video Generation

May 28, 2026cs.AI

Moment-KV: Momentum-Based Decode-Time KV Cache Compression for Long Generation

Key-Value (KV) cache remains a major bottleneck for deploying Large Language Models (LLMs) in long-generation tasks. Prior work often applies uniform compression across both prefill and decoding caches, but compressing the prefill cache degrades performance by corrupting critical context. While preserving the prefill cache is essential, decoding-phase compression remains underexplored, with existing methods relying on rigid recency windows or instantaneous attention. Our analysis of attention dynamics reveals strong temporal patterns: critical tokens receive sustained attention over long horizons, while local reasoning involves short-lived bursts. Static heuristics fail to capture this behavior, leading to premature eviction of important tokens or retention of stale ones. We propose Moment-KV, a decoding-time KV cache compression method based on momentum-driven temporal attention aggregation. Our method models token importance as a continuously evolving state, where attention is aggregated with decay, capturing both long-term influence and recent relevance. Experiments show that Moment-KV significantly improves generation fidelity in long-generation tasks (2.3-3.2 %) while maintaining decoding latency.

Soumyadeep Jana, Sagar Nishad, Sanasam Ranbir Singh

Indian Institute of Technology Guwahati, India

KV Caching Long-Context Language Modeling KV-Cache Eviction KV-Cache Compression

May 27, 2026cs.AI

CIVIC: End-to-End Sequence Compactness for Efficient Vision-Language Models

Vision-Language Models (VLMs) face severe memory and latency bottlenecks due to high-resolution visual tokens. While current token reduction methods theoretically save FLOPs, post-hoc pruning introduces structural overhead, failing to yield proportional wall-clock acceleration. However, enforcing a contiguous compact pathway risks geometric disorientation and loss of fine-grained localization. To overcome these barriers, this paper introduces CIVIC, a path-consistent compact visual inference framework. By maintaining compact sequence representations seamlessly across the vision encoder, projection layer, LLM prefill, and KV-cache, CIVIC avoids non-contiguous memory access and localized unmerging overheads. Evaluated on the Qwen3-VL architecture, CIVIC successfully translates sequence reductions into genuine physical hardware efficiency, shrinking KV-cache memory to approximately one-third of the baseline and reducing end-to-end inference latency. Enabled by text-aligned KL distillation and an adaptive spatial retention floor, CIVIC achieves these efficiency milestones without degrading accuracy across rigorous multimodal reasoning and visual grounding benchmarks.

Fengze Yang, Bo Yu, Xuewen Luo +2

Department of Civil & Environmental Engineering University of Utah 201 Presidents’ Cir, Salt Lake City, UT 84112, USA

Efficient VLM Inference KV-Cache Compression Visual Token Pruning Visual Token Compression

May 26, 2026cs.CL

UNIQUE: Universal Top-k Sparse Attention for Training-free Inference and Sparsity-aware Training

Long-context inference in large language models (LLMs) is bottlenecked by the linear growth of the self-attention key-value (KV) cache. Top-k sparse attention alleviates this by loading only a small fraction of the KV cache, but accurately and cheaply estimating cache importance, for both training-free use and sparsity-aware training, remains challenging. This paper proposes UNIQUE, a universal top-k sparse attention framework that addresses both requirements and stays consistently effective across LLM modalities. UNIQUE operates at the granularity of KV pages and estimates per-page importance with a simple yet accurate score combining the mean of the page's keys as a representative vector with their standard deviation as an offset term. To further close the train-inference gap, this paper introduces a soft-mask sparsity-aware training scheme that uses the top-k score boundary as a per-query threshold and a sigmoid soft mask around it, requiring neither auxiliary losses nor architectural changes. Experiments on text and speech LLMs show that UNIQUE preserves task performance on long-context benchmarks such as LongBench Pro and on long-form speech recognition, while delivering up to 11.4x attention-kernel speedup over FlashInfer dense attention and at least 5.3x end-to-end decoding speedup over a vLLM-based dense model.

Keqi Deng, Shaoshi Ling, Ruchao Fan +1

Microsoft, USA

Self-Attention Long-Context Language Model Inference LLM Inference Acceleration Sparse Attention KV-Cache Compression

May 26, 2026cs.LG

Hurwitz Quaternion Multiplicative Quantization for KV Cache Compression

We propose \textbf{Hurwitz Quaternion Multiplicative Quantization (HQMQ)}, a \textbf{calibration-free} method for KV cache compression of large language models. HQMQ treats each 4-element chunk of K or V as a quaternion and quantizes its unit direction to the \emph{product}

q_p \cdot q_s

, where

q_p

ranges over the 24-element Hurwitz group

2T

(the 24 vertices of the 24-cell on

S^3

, pairwise angle

60^\circ

) and

q_s

ranges over a per-(layer, head) secondary codebook of

S

\emph{random} unit quaternions. The multiplicative composition yields

24S

effective codewords at

S

stored parameters; random initialization suffices because left-multiplication is an

S^3

isometry, so seeded codebooks vary in end-task ppl by

<1.5\%

. A per-batch median-multiplier outlier extraction step (

C{=}3

, no calibration) handles modern outlier-heavy architectures. We evaluate on five modern open models: Mistral-7B (dense MHA), Llama-3-8B and Qwen2.5-7B and Qwen3-8B (dense GQA), and gpt-oss-20b (sparse MoE). On Mistral-7B and Qwen3-8B, HQMQ matches fp16 within

0.02

--

0.03

ppl points at

\sim

5 bits. On Qwen2.5-7B and Qwen3-8B, where naive int4 collapses to

10^4{+}

ppl, HQMQ + Med3

\times

recovers fp16 quality within

0.02

--

0.10

ppl points at

\sim

5 bits. HQMQ Pareto-dominates naive int by

3

--

1900\times

at matched bits across all five models, and downstream zero-shot accuracy matches fp16 at

3.79

bits on Mistral. Against the strongest calibrated KV-quantization baseline, HQMQ at

3.79

bits matches KIVI-4 (

\sim 4.5

bits) within

{\sim}1

pt on CoQA,

0.6

pts on TruthfulQA, and

2.3

pts on GSM8K, at

16\%

fewer bits and without a calibration pass. At the storage level, HQMQ delivers up to

5.05\times

KV compression, shrinking a Llama-3-70B 128k-context cache from 43 GB to 8.5 GB.

Kabir Swain, Sijie Han, Daniel Karl I. Weidele +3

Massachusetts Institute of Technology, Cambridge, MA, USA · University of Toronto, Toronto, Canada · IBM Research, Cambridge, MA, USA.

LLM Quantization KV Caching KV-Cache Compression KV-Cache Quantization Post-Training Quantization Neural Network Quantization

May 26, 2026cs.AI

OmniMem: Perturbation-aware Memory Compression for Streaming Audio-Visual LLMs

Audio-visual large language models (LLMs) hold strong promise for long-form video understanding, yet their long-video inference is fundamentally limited by the linear growth of video tokens and key-value (KV) caches. We present OmniMem, a memory-efficient streaming framework designed specifically for audio-visual LLMs. Unlike existing compression methods that treat all tokens uniformly, OmniMem introduces a modality-aware memory allocation strategy that separately manages visual and audio contexts, addressing the severe token imbalance between the two modalities. OmniMem further preserves informative and non-redundant KV states through perturbation-aware memory selection, enabling compact memory without sacrificing long-range understanding. To strengthen compression under realistic deployment constraints, we also explore budget-aware fine-tuning, which encourages the model to consolidate useful information into retained memory. Experiments on VideoMME Long, LVBench, and LVOmniBench with video-SALMONN 2+ and Qwen-2.5-Omni show that OmniMem consistently improves over strong training-free compression baselines by 2-4% absolute accuracy under the same memory budgets, with an additional 1-2% gain after fine-tuning.

Guangzhi Sun, Yixuan Li, Yudong Yang +1

ByteDance · Department of Engineering, University of Cambridge · Tsinghua University

Streaming Video Understanding Multimodal Large Language Models Multimodal Token Compression KV-Cache Compression Video Token Compression

May 26, 2026cs.CL

NestedKV: Nested Memory Routing for Long-Context KV Cache Compression

Long-context language models are limited by the memory footprint of the key-value (KV) cache. Existing training-free KV compression methods usually rank tokens by one importance signal -- attention, recency, layer-wise allocation, or key distinctiveness -- which becomes brittle when useful context is globally distinctive, locally episodic, or immediately relevant. We introduce NestedKV, a key-only KV cache compression method inspired by the Continuum Memory System in Nested Learning. NestedKV maintains global, block-level, and sliding-window key anchors, scores tokens by multi-time-scale cosine anomaly, and combines the resulting rankings with a training-free outer learner using head-adaptive mixing and surprise-gated token routing. The score is paired with adaptive per-head budgets and requires no training or LLM modification. Across RULER (4k--32k), LooGLE, LongBench, LongBench-E, InfiniteBench, and MMLU-Pro on Qwen3 and Llama-3.2 models, NestedKV is strongest when the retained cache is small. On Qwen3-4B, it improves over KeyDiff by up to 19.10 points on RULER and 19.29 on LongBench at

r=0.75

; at

r=0.95

, it retains 37.32 on LongBench versus 17.55 for KeyDiff.

Hong Chen, Xiang Liu, Yubo Gao +5

The Hong Kong University of Science and Technology (Guangzhou) · Jimei University

KV Caching Long-Context Language Modeling LLM Inference Acceleration KV-Cache Compression

May 24, 2026cs.IT

Polynomial Context-Truncation Sensitivity in Autoregressive Language Models: Sequential Wyner-Ziv Bounds for KV Cache Compression

We study the rate-distortion limits of online KV cache compression in autoregressive language models, formulating it as sequential Wyner-Ziv source coding on the filtration induced by the model, with the next-step query as decoder side information. Empirically, across four models spanning two families and

0.5

-

3

B parameters, we find that the next-token distribution's sensitivity to context truncation decays \emph{polynomially} rather than \emph{geometrically}: a power law improves on an exponential fit by an order of magnitude in extrapolation, the fitted exponent is recovered independently from a sink-plus-recent KL measurement, and the decay is verified to be free of positional-encoding artifacts by a position-preserving ablation. Under a corresponding \emph{polynomial truncation-sensitivity} assumption, our main result characterizes the per-token memory requirement of \emph{suffix-only} cache policies: a sliding-window scheme attains distortion

\varepsilon

with window

w = O(\varepsilon^{-1/α})

, and -- under an additional two-sided Bayes-risk condition -- a converse shows

w = Ω(\varepsilon^{-1/α})

is necessary within this policy class, so the scaling is

Θ(\varepsilon^{-1/α})

for suffix-only policies. Whether recurrent or propagating cache summaries can beat this scaling is left open. An explicit block-Markov scheme achieves the upper bound; its rate-of-convergence exponent matches the converse under additional forward-decay and regularity hypotheses (not implied by truncation sensitivity alone), and differs by a factor of two otherwise. Empirically, the polynomial law predicts the degradation curves of concrete cache policies: recency-based eviction (sliding, sink-plus-recent) suppresses distortion by roughly two orders of magnitude over random retention at equal budget, with a power-law decay in the budget.

Munsik Kim

Independent Researcher.

KV Caching Rate-Distortion Theory Autoregressive Language Modeling Rate-Distortion Optimization KV-Cache Compression

May 22, 2026cs.LG

A Simple Plug-in for Improving Eviction-Based KV Cache Compression

KV cache growth is a major bottleneck for long-context inference in large language models. Existing methods are often dominated by binary eviction or representation approximation, which may underutilize tokens that are not critical for exact retention but are still reconstructable. We present VECTOR, a plug-and-play augmentation for eviction-based pipelines that introduces three-way token routing: retention, approximation, and eviction. VECTOR combines an importance signal from the base scorer with a reconstructability signal from an offline-calibrated regression-based value estimation. By leveraging reconstructability, VECTOR recovers useful value information that would otherwise be irreversibly lost under binary eviction, while preserving key vectors for attention routing stability. Experimental results show that VECTOR improves quality-memory trade-offs under medium-to-high compression, with especially clear gains in stricter budget regimes.

Yuping Lin, Jiayuan Ding, Yue Xing +3

1Michigan State University · 2Hippocratic AI

KV Caching Memory-Efficient Optimization KV-Cache Eviction LLM Inference Acceleration KV-Cache Compression

May 22, 2026cs.LG

Adaptive Mass-Segmented KV Compression for Long-Context Reasoning

The linear growth of the Key-Value (KV) cache is a critical bottleneck in long-form LLM inference. Existing KV compression methods mitigate this by evicting tokens based on importance scores. However, we show that their reliance on global Top-k selection triggers Region Wipe-out: the severe eviction of contiguous reasoning blocks that derails logical coherence. To address this, we propose Adaptive Mass-Segmented (AMS) KV Compression, a framework that shifts the paradigm from token-level competition to region-aware quota allocation. AMS adaptively partitions the KV cache based on the spatial distribution of attention mass, ensuring structurally vital reasoning segments receive guaranteed memory quotas. To ensure stability during iterative decoding, an EMA-based smoothing mechanism is incorporated to prevent jitter in segment boundaries. Crucially, AMS is a universal plug-and-play layer that is orthogonal to existing scorers. It can be seamlessly integrated into representative methods such as TOVA, Expected Attention, KeyDiff, R-KV and TriAttention. AMS is also system-compatible with modern paged-KV serving frameworks such as vLLM, supporting efficient gather-and-compact KV execution without introducing additional steady-state attention overhead. Extensive experiments across a diverse suite of tasks, including mathematical reasoning (MATH500, AIME, GSM8K), code completion, open-domain QA, and sparse retrieval, demonstrate that AMS consistently mitigates structural fragmentation and boosts model performance.

Junzhe Yang, Xiaoyu Shen

Shanghai Jiao Tong University · Institute of Digital Twin, Eastern Institute of Technology, Ningbo

KV Caching Long-Context Language Model Inference Memory-Efficient Inference KV-Cache Compression Long-Context Inference KV-Cache Pruning

May 21, 2026cs.CV

WorldKV: Efficient World Memory with World Retrieval and Compression

Autoregressive video diffusion models have enabled real-time, action-conditioned world generation. However, sustaining a persistent world, where revisiting a previously seen viewpoint yields consistent content, remains an open problem. Full KV-cache attention preserves this consistency but breaks real-time constraints: memory footprint and attention cost grow linearly with rollout length. Sliding window inference restores throughput but discards long-term consistency. We propose WorldKV, a training-free framework with two components: World Retrieval and World Compression. World Retrieval stores evicted KV-cache chunks in GPU/CPU memory and selectively retrieves scene-relevant chunks via camera/ action correspondence, inserting them back into the native attention window without re-encoding. World Compression prunes redundant tokens within each chunk via key-key similarity to an anchor frame, halving per-chunk storage to fit 2x more history under a fixed budget. On Matrix-Game-2.0 and LingBot- World-Fast, WorldKV matches or exceeds full-KV memory fidelity at roughly 2x the throughput, and is competitive with memory-trained baselines without any fine-tuning. Project Page: https://cvlab-kaist.github.io/WorldKV/

Jung Yi, Minjae Kim, Paul Hyunbin Cho +3

1KAIST AI · 2Naver AI Lab

KV Caching Memory-Augmented Video Generation Action-Conditioned World Models Efficient Inference for World Action Models Diffusion Model Caching KV-Cache Compression+3