Kamera: Unified Position-Invariant Multimodal KV Cache for Training-Free Reuse

• URL: http://arxiv.org/abs/2606.23581v1
• Date: Mon, 22 Jun 2026 16:47:00 GMT
• Title: Kamera: Unified Position-Invariant Multimodal KV Cache for Training-Free Reuse
• Abstract summary: Multimodal agents repeatedly re-examine the same video frames, UI screenshots, and rendered artifacts as their context window slides.<n>We show this recompute is avoidable, and identify exactly what naive KV reuse loses.<n>Blind reuse therefore leaves single-hop recall intact while halving multi-hop accuracy.<n>We repair it with a small, training-free low-rank conditioning patch stored alongside each position-free chunk.
• Score: 1.081571058570587
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multimodal agents repeatedly re-examine the same video frames, UI screenshots, and rendered artifacts as their context window slides and reasoning iterates, yet every look-back re-encodes from scratch, because prefix caches serve reuse only at a fixed leading position. We show this recompute is avoidable, and identify exactly what naive KV reuse loses: the cross-chunk conditioning a chunk absorbs from its neighbours. This loss is asymmetric. The direct readout of a cached chunk is recovered exactly and for free by the standard state-merge. What remains is a diffuse, low-rank residue concentrated in deep layers, invisible to single-hop retrieval but precisely what multi-hop reasoning binds on. Blind reuse therefore leaves single-hop recall intact while halving multi-hop accuracy; this is the failure mode prior position-independent caches, designed for single-context or single-image reuse, do not address. We repair it with a small, training-free low-rank conditioning patch stored alongside each position-free chunk. Reuse reduces to one operator across MLA, GQA, and MHA: exact RoPE re-rotation to any target position, plus the patch that restores cross-chunk binding. This makes three window operations cheap: reorder (one patch serves every ordering of a cached set), sliding-window survival (surviving chunks relocate via rotation only, zero re-encode), and recall (an evicted chunk is rehydrated by its patch, never re-encoded). A rank-m patch recovers full task accuracy on cross-chunk-binding benchmarks, MM-NIAH across two attention families and two-page doc-QA, at a fraction of the KV footprint, and reconstructs re-prefill KV to within bf16 rounding in a production SGLang kernel across six backbones. The conditioning signal is strongest in redundant vision and video streams, making our solution most impactful where multimodal agents spend their recompute budget.

Related papers

• KVShareArena: KV-Cache Reuse Across Contexts and Model Checkpoints [14.86076891340077]
  KVShare-cache reuse across prompt contexts and model checkpoints on retrieved chunks and agent reports.<n>We find that correcting positions, which needs no recomputation, is enough until a question needs several sources at once.<n> KVArena-cache scores every method by the fraction of the gap it recovers between no cache and full recomputation.
  arXiv  Detail & Related papers  (2026-09-09T14:53:45Z)
• Back from the Future: Key-Value Cache Management by Counter-Causal Surprise [67.1056509495879]
  Key-value (KV) cache management through compression and eviction strategies has emerged as an important research direction in recent years.<n>We propose a simple yet effective KV eviction scheme motivated by the insight that past tokens which can be well-predicted from more recent tokens are redundant.<n>We evaluate our strategy on various open-source LLMs and benchmark datasets showing competitive or improved performance over other state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-07-30T02:42:51Z)
• Position Rebinding Cache Reuse: Replay-Free Visual Revisiting for Interleaved Multimodal Reasoning [51.563653495547335]
  multimodal reasoning improves visual grounding by revisiting visual evidence during multi-step generation.<n>We propose Position Rebinding Cache Reuse (PRCR), a cache-level framework for replay-free visual revisiting.<n>PRCR achieves replay-level or better performance, improving average accuracy by 5 percent and reducing visual-revisiting by up to tens of thousands of times.
  arXiv  Detail & Related papers  (2026-06-25T05:47:52Z)
• GRKV: Global Regression for Training-Free KV Cache Compression in Long-Context LLMs [97.36238579001544]
  Large language models (LLMs) with extended context lengths rely on the key-value ( KV) cache to support attention over prior tokens.<n>Maintaining the KV cache incurs substantial memory overhead, motivating KV-cache compression methods.<n>We propose GRKV, a training-free KV-cache merging method that directly minimizes the discrepancy between compressed-cache and full-cache attention outputs.
  arXiv  Detail & Related papers  (2026-05-29T10:16:30Z)
• Probing the Prompt KV Cache: Where It Becomes Dispensable [9.529147118376464]
  Prior KV cache compression schemes empirically demonstrate that the prompt cache is partially redundant during decoding, dropping or summarising entries with little accuracy loss.<n>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.<n>A controlled splice intervention swept over layer cutoff and decoding steps shows this redundancy is about form (chat template scaffolding) rather than content.
  arXiv  Detail & Related papers  (2026-05-28T21:07:41Z)
• WorldKV: Efficient World Memory with World Retrieval and Compression [56.57011243315561]
  We propose WorldKV, a training-free framework with two components: World Retrieval and World Compression.<n>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.
  arXiv  Detail & Related papers  (2026-05-21T16:55:04Z)
• AgentKVShift: Efficient KV Cache Reuse for Agentic Memory Systems [15.913507689262573]
  AgentKVShift is a training-free, probe-guided residual correction method that operates per retrieved memory unit.<n>We show that AgentKVShift achieves near full recompute performance while refreshing only 10-30% of the cache.<n>It requires up to 5x lower recompute to reach this near-full performance, which prior reuse methods only attain at 45-55% refresh.
  arXiv  Detail & Related papers  (2026-05-15T16:29:36Z)
• Make Each Token Count: Towards Improving Long-Context Performance with KV Cache Eviction [65.710271475739]
  We introduce a global retention-based KV eviction method that learns each token's future utility under a unified memory budget.<n>We show that our method substantially reduces KV memory while matching or surpassing full-cache inference.<n>These results suggest that learned, globally calibrated KV eviction is not only a compression technique, but also a mechanism for improving long-context reasoning.
  arXiv  Detail & Related papers  (2026-05-10T16:47:50Z)
• Sparse Prefix Caching for Hybrid and Recurrent LLM Serving [0.7284556903703034]
  We formalize sparse prefix caching as checkpoint placement under a distribution over overlap depths.<n>For use cases where requests share a non-trivial prefix, we show that our method consistently improves the frontier traced by standard asymmetry on real-world data.<n>It preserves exact outputs, does not change the recurrent computation itself or require new recurrent update kernels.
  arXiv  Detail & Related papers  (2026-04-17T09:24:58Z)
• RelayCaching: Accelerating LLM Collaboration via Decoding KV Cache Reuse [5.597099794399441]
  RelayCaching is a training-free inference method that directly reuses decoding phase KV caches from previous agents.<n>We show that RelayCaching achieves over 80% KV cache reuse, reduces TTFT by up to $4.7times$ compared to the standard pipeline.
  arXiv  Detail & Related papers  (2026-02-28T04:46:28Z)
• PackCache: A Training-Free Acceleration Method for Unified Autoregressive Video Generation via Compact KV-Cache [61.57938553036056]
  We introduce PackCache, a training-free KV-cache management method that compacts the KV cache through three coordinated mechanisms.<n>In terms of efficiency, PackCache accelerates end-to-end generation by 1.7-2.2x on 48-frame long sequences.
  arXiv  Detail & Related papers  (2026-01-07T19:51:06Z)
• MEPIC: Memory Efficient Position Independent Caching for LLM Serving [16.99046229452175]
  We present a memory-efficient system that enables chunk KV reuse across positions, requests, and batches.<n>MePIC aligns chunk KV to paged storage, shifts recomputation from token- to block-level so only the first block is request-specific.
  arXiv  Detail & Related papers  (2025-12-18T18:04:01Z)
• Cache-Craft: Managing Chunk-Caches for Efficient Retrieval-Augmented Generation [14.842469293627271]
  CacheCraft is a system for managing reusing precomputed KVs corresponding to the text chunks.<n>We show how to identify chunk-caches that are reusable, how to efficiently perform a small fraction of recomputation to fix the cache, and how to efficiently store and evict chunk-caches in the hardware.
  arXiv  Detail & Related papers  (2025-02-05T14:12:33Z)
• Get More with LESS: Synthesizing Recurrence with KV Cache Compression for Efficient LLM Inference [78.65321721142624]
  We focus on a memory bottleneck imposed by the key-value ( KV) cache. Existing KV cache methods approach this problem by pruning or evicting large swaths of relatively less important KV pairs. We propose LESS, a simple integration of a constant sized cache with eviction-based cache methods.
  arXiv  Detail & Related papers  (2024-02-14T18:54:56Z)

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.