KVCapsule: Efficient Sequential KV Cache Compression for Vision-Language Models with Asymmetric Redundancy

• URL: http://arxiv.org/abs/2605.16439v1
• Date: Thu, 14 May 2026 23:01:58 GMT
• Title: KVCapsule: Efficient Sequential KV Cache Compression for Vision-Language Models with Asymmetric Redundancy
• Abstract summary: Vision-Language Models (VLMs) have emerged as a critical and fast-growing extension of Large Language Models (LLMs)<n>We propose KVCapsule, a novel KV cache compression framework for vision tokens.<n>We demonstrate up to 2x improvement in TPS and 2.4x reduction in KV cache memory at a 60% compression ratio, with negligible degradation in accuracy or response quality.
• Score: 8.24188371483346
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision-Language Models (VLMs) have emerged as a critical and fast-growing extension of Large Language Models (LLMs) that enable multimodal reasoning through both text and image inputs. Although VLMs enrich the capabilities of language models, they also inherit and amplify key computational bottlenecks: the memory overhead caused by the large key-value (KV) cache during autoregressive decoding. This challenge is particularly severe in VLMs, where images produce longer token sequences and denser feature representations compared to text. Moreover, the spatial and information-rich nature of vision tokens introduces structured attention patterns that make many LLM-oriented KV cache compression techniques ineffective when applied directly to VLMs. In this work, we conduct a detailed empirical analysis of the behavior of vision tokens, highlighting the critical differences from purely text-based models. Based on these insights, we propose KVCapsule, a novel KV cache compression framework for vision tokens. KVCapsule keeps the pretrained VLM backbone frozen, requires no modification to the attention computation modules, and can be integrated into existing VLMs through lightweight compression and reconstruction components. We evaluate KVCapsule on multiple VLMs and benchmark tasks, demonstrating up to 2x improvement in TPS and 2.4x reduction in KV cache memory at a 60% compression ratio, with negligible degradation in accuracy or response quality. Our findings offer practical pathways to scale VLM inference under constrained memory budgets and inspire further research into structure-aware cache compression for multimodal models.

Related papers

• VisCache: Visual KV Cache Pruning for Efficient Vision Large Language Model Inference [17.932004205808486]
  VisCache is a framework for coarse-to-fine textbfVisual KV textbfCache pruning without training.<n>PruneKV is a surgical KV compression algorithm tailored to the attention dynamics of Vision Large Language Models.<n>VisCache consistently outperforms existing baselines.
  arXiv  Detail & Related papers  (2026-08-25T04:52:05Z)
• VisCo: Leveraging Large Language Models as Intrinsic Encoders for Visual Token Compression [52.23010472235226]
  Vision-language models (VLMs) process large numbers of visual tokens, resulting in substantial inference and overhead latency.<n>We propose VisCo, a training-efficient self-compression framework that reuses the pretrained VLM itself as an intrinsic compressor.
  arXiv  Detail & Related papers  (2026-07-14T13:21:36Z)
• MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering [75.0394545769057]
  KV-caching stores the Key-Value of the historical tokens via LLM prefill.<n>MuKV is a method that features a multi-grained KV cache compression module and a semi-hierarchical retrieval approach.<n> Experiments on long-streaming VideoQA benchmarks show that MuKV significantly improves answer accuracy, without sacrificing memory and online QA efficiency.
  arXiv  Detail & Related papers  (2026-05-21T10:13:03Z)
• Make Your LVLM KV Cache More Lightweight [32.6781862382433]
  Key-Value (KV) cache has become a de facto component of modern Large Vision-Language Models (LVLMs)<n>We propose LightKV, a novel approach that reduces KV cache size by exploiting the redundancy among vision-token embeddings.<n>We evaluate LightKV on eight open-source LVLMs across eight public benchmark datasets.
  arXiv  Detail & Related papers  (2026-05-01T17:11:39Z)
• dKV-Cache: The Cache for Diffusion Language Models [53.85291644298835]
  Diffusion Language Models (DLMs) have been seen as a promising competitor for autoregressive language models.<n>We propose a KV-cache-like mechanism, delayed KV-Cache, for the denoising process of DLMs.<n>Our approach is motivated by the observation that different tokens have distinct representation dynamics throughout the diffusion process.
  arXiv  Detail & Related papers  (2025-05-21T17:32:10Z)
• AirCache: Activating Inter-modal Relevancy KV Cache Compression for Efficient Large Vision-Language Model Inference [11.73134417321505]
  We propose AirCache, a novel KV cache compression method aimed at accelerating LVLMs inference.<n>We show that our method achieves comparable performance to the full cache while retaining only 10% of visual KV cache.
  arXiv  Detail & Related papers  (2025-03-31T11:13:18Z)
• VL-Cache: Sparsity and Modality-Aware KV Cache Compression for Vision-Language Model Inference Acceleration [7.463830743649754]
  Vision-Language Models (VLMs) have demonstrated impressive performance across a versatile set of tasks. Key-Value (KV) cache encodes long visual contexts, such as images or videos. Existing KV cache compression methods are effective for Large Language Models (LLMs) We propose a novel KV cache compression recipe tailored for accelerating VLM inference.
  arXiv  Detail & Related papers  (2024-10-29T20:04:34Z)
• LoRC: Low-Rank Compression for LLMs KV Cache with a Progressive Compression Strategy [59.1298692559785]
  Key-Value ( KV) cache is crucial component in serving transformer-based autoregressive large language models (LLMs) Existing approaches to mitigate this issue include: (1) efficient attention variants integrated in upcycling stages; (2) KV cache compression at test time; and (3) KV cache compression at test time. We propose a low-rank approximation of KV weight matrices, allowing plug-in integration with existing transformer-based LLMs without model retraining. Our method is designed to function without model tuning in upcycling stages or task-specific profiling in test stages.
  arXiv  Detail & Related papers  (2024-10-04T03:10:53Z)
• ThinK: Thinner Key Cache by Query-Driven Pruning [63.13363917871414]
  Large Language Models (LLMs) have revolutionized the field of natural language processing, achieving unprecedented performance across a variety of applications.<n>This paper focuses on the long-context scenario, addressing the inefficiencies in KV cache memory consumption during inference.<n>We propose ThinK, a novel query-dependent KV cache pruning method designed to minimize attention weight loss while selectively pruning the least significant channels.
  arXiv  Detail & Related papers  (2024-07-30T17:59:08Z)
• Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs [82.08922896531618]
  We introduce adaptive KV cache compression, a plug-and-play method that reduces the memory footprint of generative inference for Large Language Models (LLMs) We conduct targeted profiling to discern the intrinsic structure of attention modules. Based on the recognized structure, we then construct the KV cache in an adaptive manner: evicting long-range contexts on attention heads emphasizing local contexts, discarding non-special tokens on attention heads centered on special tokens, and only employing the standard KV cache for attention heads that broadly attend to all tokens.
  arXiv  Detail & Related papers  (2023-10-03T05:17:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.