Position Rebinding Cache Reuse: Replay-Free Visual Revisiting for Interleaved Multimodal Reasoning

• URL: http://arxiv.org/abs/2606.26631v1
• Date: Thu, 25 Jun 2026 05:47:52 GMT
• Title: Position Rebinding Cache Reuse: Replay-Free Visual Revisiting for Interleaved Multimodal Reasoning
• Abstract summary: 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.
• Score: 51.563653495547335
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Interleaved multimodal reasoning improves visual grounding by revisiting visual evidence during multi-step generation, yet existing methods typically rely on token replay, repeatedly forwarding selected visual tokens. A natural shortcut is to reuse the historical visual key-value (KV) cache directly. However, we identify a critical failure mode of this strategy: cached visual keys are already bound to their original positional context. Such stale positional binding distorts attention under later decoding contexts and can trigger severe autoregressive decoding collapse. This failure suggests that effective cache reuse requires reconstructing visual evidence under positions compatible with the current decoding state, rather than directly copying position-bound historical cache entries. To this end, we propose Position Rebinding Cache Reuse (PRCR), a cache-level framework for replay-free visual revisiting. PRCR stores raw visual KV cache together with their original spatial coordinates, then reassigns position-compatible coordinates to select entries and rebinds their keys before injecting the reconstructed cache into the active decoder cache. This design reuses historical visual evidence while preserving textual positional continuity and relative visual structure. Experiments across multiple multimodal reasoning benchmarks show that PRCR achieves replay-level or better performance, improving average accuracy by 5 percent and reducing visual-revisiting computation by up to tens of thousands of times.

Related papers

• LayerRecall: A State-Conditioned Memory Router for Long-Horizon Consistency in Video Generation [22.878882105342182]
  Autoregressive video diffusion produces chunks from a bounded recent context.<n>Recency-based caching evicts historical cues needed when subjects, objects, scenes, or attributes reappear.<n>LayerRecall retrieves relevant historical K/V states and injects them only into backbone-specific memory-sensitive layers.
  arXiv  Detail & Related papers  (2026-08-28T15:49:13Z)
• ReCache: Efficient KV Cache Reuse and Compression for Tool-Augmented LLM Agents [7.368551130048085]
  textbfReCache is a framework for independently caching resource representations.<n>We evaluate ReCache on a benchmark assembled from seven public tool- and skill-use datasets.
  arXiv  Detail & Related papers  (2026-08-20T05:57:24Z)
• Addressable Memory for Video World Models [50.40232922140905]
  We study visual persistence in interactive video world models.<n>We propose WorldTrace, a training-free memory framework for long-horizon visual persistence.
  arXiv  Detail & Related papers  (2026-08-07T16:55:57Z)
• 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)
• Latent Visual Cache for Video Reasoning [64.44259870076141]
  We introduce Latent Video Cache (Latent-VC), a recurrent latent visual cache inserted into the decoder to preserve compact visual memories throughout reasoning.<n>Latent-VC consistently outperforms strong CoT and SFT+ GRPO baselines across six video benchmarks.<n>It also achieves higher accuracy with substantially shorter responses.
  arXiv  Detail & Related papers  (2026-07-01T13:51:02Z)
• Kamera: Unified Position-Invariant Multimodal KV Cache for Training-Free Reuse [1.081571058570587]
  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.
  arXiv  Detail & Related papers  (2026-06-22T16:47:00Z)
• FadeMem: Distance-Aware Memory Consolidation for Autoregressive Video Diffusion [59.207505503284715]
  FadeMem organizes historical KV blocks into a temporal hierarchy under a fixed cache budget.<n>New history is inserted as fine-grained entries, while older adjacent entries are progressively merged.<n>Experiments show improved subject consistency, background stability, and temporal coherence over existing bounded-cache strategies.
  arXiv  Detail & Related papers  (2026-06-09T10:22:18Z)
• Echo-Memory: A Controlled Study of Memory in Action World Models [58.77172260403133]
  We present a controlled study of memory mechanisms in action-conditioned world models.<n>Existing memory designs are hard to compare because gains are entangled with backbone, training, retrieval, and evaluation differences.<n>We use Echo-Memory to fix the action-to-video interface and varies only how history is stored and read by the generator.
  arXiv  Detail & Related papers  (2026-06-08T17:54:10Z)
• CoRDS: Coreset-based Representative and Diverse Selection for Streaming Video Understanding [30.287018710590257]
  Streaming video understanding with large vision-language models (VLMs) requires a compact memory that can support future reasoning over an ever-growing visual history.<n>A common solution is to compress the key-value (KV) cache, but existing streaming methods typically rely on local token-wises.<n>We propose to view KV-cache compression as a coreset selection problem, rather than scoring tokens independently for retention.
  arXiv  Detail & Related papers  (2026-05-14T03:22:30Z)
• Decouple and Cache: KV Cache Construction for Streaming Video Understanding [53.55135022958052]
  Streaming video understanding requires processing unbounded video streams with limited memory and computation.<n>We propose Decoupled Streaming Cache(DSCache), a training-free cache construction mechanism that adapts pretrained offline models to streaming settings.<n> Experiments on Streaming Video QA benchmarks demonstrate DSCache's state-of-the-art performance, with an average 2.5% accuracy gains over prior methods.
  arXiv  Detail & Related papers  (2026-05-03T13:02:44Z)
• 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)
• 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)
• Advancing Cache-Based Few-Shot Classification via Patch-Driven Relational Gated Graph Attention [3.4693817403659515]
  Few-shot image classification remains difficult under limited supervision.<n>Recent cache-based adaptation approaches (e.g., Tip-Adapter) address this challenge to some extent.<n>We introduce a novel patch-driven relational refinement that learns cache adapter weights from intra-image patch dependencies.
  arXiv  Detail & Related papers  (2025-12-13T23:53:00Z)
• KV Cache Recycling to Expand Usable Context Capacity in Low Parameter LLMs [2.261486598306908]
  We build a cache of past activations and get entries by sentence embeddings, then reuse cached past key values when the cached prompt is an exact prefix of the new input.<n>We compare recycled vs. baseline runs on latency and output fidelity, and log reuse depth in tokens.<n>In tests, we observe consistent speedups when prefix overlap exists, with no material degradation in output semantics, and when overlap is absent.
  arXiv  Detail & Related papers  (2025-12-04T17:04:43Z)
• Efficient Inference of Vision Instruction-Following Models with Elastic Cache [76.44955111634545]
  We introduce Elastic Cache, a novel strategy for efficient deployment of instruction-following large vision-language models. We propose an importance-driven cache merging strategy to prune redundancy caches. For instruction encoding, we utilize the frequency to evaluate the importance of caches. Results on a range of LVLMs demonstrate that Elastic Cache not only boosts efficiency but also notably outperforms existing pruning methods in language generation.
  arXiv  Detail & Related papers  (2024-07-25T15:29:05Z)

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.