Latent Visual Cache for Video Reasoning

• URL: http://arxiv.org/abs/2607.02607v1
• Date: Wed, 01 Jul 2026 13:51:02 GMT
• Title: Latent Visual Cache for Video Reasoning
• Abstract summary: 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.
• Score: 64.44259870076141
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Video reasoning requires Large Multimodal Models (LMMs) to remain grounded in dense evidence, yet existing systems largely adopt "read-once, generate-many" paradigm, in which visual grounding weakens during generation. This phenomenon has been widely observed and is known as Visual Anchoring Decay. To fill this gap, we introduce Latent Video Cache (Latent-VC), a recurrent latent visual cache inserted into the decoder to preserve compact visual memories throughout reasoning. The cache is trained with supervised contrastive cache alignment and vision-grounded GRPO with a latent grounding reward, while maintaining strict train-inference alignment through native decoder hidden states. Built on Qwen3.5-9B, Latent-VC consistently outperforms strong CoT and SFT+GRPO baselines across six video benchmarks, with especially clear gains on grounding-intensive and long-video tasks. In addition, it also achieves higher accuracy with substantially shorter responses, suggesting that latent visual caching improves video reasoning by preserving visual evidence rather than relying on longer textual chains.

Related papers

• StreamFlow: Dynamic Memory Flows for Streaming Video Understanding [65.10324190760602]
  StreamFlow is an efficient visual memory framework that enables dynamic, on-demand access to historical visual information.<n>It achieves state-of-the-art streaming video understanding performance, reaching 67.73% overall accuracy on StreamingBench.<n>Relative to the vanilla setting, it improves the visual attention score (VAS) by 59.1% while reducing end-to-end latency and peak memory by 50.4% and 21.1%, respectively.
  arXiv  Detail & Related papers  (2026-08-11T14:19:03Z)
• 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)
• TetherCache: Stabilizing Autoregressive Long-Form Video Generation with Gated Recall and Trusted Alignment [51.33418612284208]
  We propose TetherCache, a training-free and plug-and-play cache management strategy for drift-resistant long video generation.<n>Gated Recall with Attention-Diversity Balancing selects long-range memory frames using a gated score.<n>TAME lightly edits newly recalled memory tokens by aligning their statistics to a trusted context distribution.
  arXiv  Detail & Related papers  (2026-06-11T08:16:08Z)
• SWIFT: Prompt-Adaptive Memory for Efficient Interactive Long Video Generation [31.105007908298003]
  Streaming long-video generation faces a central challenge in continuous semantic switching.<n>Current approaches rely on cache rebuilding at prompt boundaries or fixed memory budgets.<n>We present SWIFT, a training-free framework for multi-prompt long-video generation.
  arXiv  Detail & Related papers  (2026-05-10T09:37:56Z)
• 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)
• Fast Autoregressive Video Diffusion and World Models with Temporal Cache Compression and Sparse Attention [37.91838955436801]
  Autoregressive video diffusion models enable streaming generation, opening the door to long-form synthesis, video world models, and interactive neural game engines.<n>As generation progresses, the KV cache grows, causing both increasing latency and escalating GPU memory, which in turn restricts usable temporal context and harms long-range consistency.<n>We propose a unified, training-free attention framework for autoregressive diffusion: TempCache compresses the KV cache via temporal correspondence to bound cache growth; AnnCA accelerates cross-attention by selecting frame-relevant prompt tokens using fast approximate nearest neighbor matching; and AnnSA sparsifies self-attention by restricting each query
  arXiv  Detail & Related papers  (2026-02-02T08:31:21Z)
• 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)
• VideoMem: Enhancing Ultra-Long Video Understanding via Adaptive Memory Management [17.645183933549458]
  VideoMem is a novel framework that pioneers models long video understanding as a sequential generation task via adaptive memory management.<n>We show that VideoMem significantly outperforms existing open-source models across diverse benchmarks for ultra-long video understanding tasks.
  arXiv  Detail & Related papers  (2025-12-04T07:42:13Z)
• Open-o3 Video: Grounded Video Reasoning with Explicit Spatio-Temporal Evidence [70.2803680525165]
  We introduce Open-o3 Video, a non-agent framework that integrates explicit evidence into video reasoning.<n>The model highlights key objects and bounding boxes alongside its answers, allowing reasoning to be grounded in concrete visual observations.<n>On V-STAR benchmark, Open-o3 Video achieves state-of-the-art performance, raising mAM by 14.4% and mL timestamp by 24.2%.
  arXiv  Detail & Related papers  (2025-10-23T14:05:56Z)

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.