cs.CVNov 18, 2026

CanopyKV: Remember beyond the Crop for Fast Active Visual Reasoning

Authors: Lei Yang, Dayan Wu, Yiliang Zhu, Xinze Liu, Hengjie Zhu, Zihao Zhang, Ding Wang, Peng Fu, 

Organizations: Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China · School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China · Department of Applied Mathematics and Statistics, John Hopkins University, Baltimore, MD, USA

Abstract

Active visual reasoning enables multimodal models to answer challenging visual questions by gathering fine-grained evidence through iterative image inspection and tool use. However, accumulating crops and reasoning tokens expands the key-value (KV) cache, making compression important for reducing memory and inference costs. Existing KV compression methods typically select historical tokens based on attention, recency, or redundancy. These criteria do not explicitly distinguish locally replaced evidence from complementary information needed for future exploration: each crop refreshes a local region, while earlier views may still support subsequent decisions. Discarding such evidence can impair accuracy or require additional search, while scoring and cache reorganization can offset the computational savings from compression. We introduce CanopyKV, a training-free KV compression framework that uses parent-child crop relationships to retain complementary evidence, keeps retained history stable, and protects the state needed for ongoing reasoning. Tool metadata provides retention signals without additional attention scoring, while compact KV storage reduces subsequent attention costs. Across VisualProbe, V*, HR-Bench, and MME-Lite, CanopyKV achieves state-of-the-art answer accuracy and end-to-end efficiency among the evaluated KV compression methods. On MME-Lite, it retains approximately one-quarter of Dense's total KV while improving accuracy by 10.5 percentage points and accelerating complete reasoning by 1.64×1.64\times.

Figures & tables

Appendix figures & tables10 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Nov 11, 2026

TraceKV: Policy-Preserving Low-Rank KV Cache Compression for Reasoning Vision-Language Models

Reasoning vision-language models (VLMs) impose substantial KV cache demands from both large multimodal contexts and growing reasoning traces. Low-rank KV compression has emerged as a promising paradigm that stores low-dimensional latents of KV states and can be combined with quantization. However, existing low-rank methods often induce growing predictive policy drift from the dense model when compressing reasoning KV states, resulting in reasoning failures. We identify two key causes of this degradation: calibration-state mismatch between static contexts and on-policy reasoning states, and unequal error sensitivity across KV states. To address these challenges, we propose TraceKV, a training-free low-rank KV compression framework that unifies on-policy calibration, sensitivity-aware SVD, and global rank allocation under a single policy-preserving principle, substantially reducing policy-KL divergence during reasoning. Experiments across multiple VLMs and visual reasoning benchmarks demonstrate superior accuracy--memory trade-offs, achieving near-lossless reasoning accuracy with 5.64×\times KV cache compression when combined with quantization. Optimized low-rank attention kernels further deliver up to 1.83×\times end-to-end decoding speedup. Code will be available at https://github.com/AK-DREAM/TraceKV.
Sep 4, 2026

BeaconKV: Key-Value Cache Compression Guided by Beacon Queries for Efficient Large Reasoning Model Inference

Large Reasoning Models (LRMs) achieve superior problem-solving through extended Chain-of-Thought (CoT) generation, but the resulting key-value (KV) cache grows linearly with sequence length and creates severe memory bottlenecks, often exceeding GPU capacity for long reasoning traces. Existing KV cache compression methods rely on recent queries to estimate future token importance, implicitly assuming these serve as reliable proxies for future attention patterns. We demonstrate that this assumption fails in long-horizon reasoning: certain decoding steps generate Thought Revisiting Tokens (TRT) that re-attend to distant previous context, such as task-solving plans formulated early in the trace. Through systematic analysis, we discover that queries corresponding to the TRT cluster into a small number of similarity groups in the embedding space. Based on this insight, we propose BeaconKV, a training-free KV cache compression method that maintains beacon queries, compact representatives for each global query cluster, to anticipate which KV pairs will be revisited without storing the entire query history. Across four open-source LRMs and diverse reasoning benchmarks, BeaconKV generally outperforms existing compression methods, achieving up to 5.8×5.8\times memory reduction while nearly preserving full cache accuracy and improving throughput by over 4.3×4.3\times.
Aug 25, 2026

VisCache: Visual KV Cache Pruning for Efficient Vision Large Language Model Inference

While Vision Large Language Models (VLLMs) have achieved remarkable success in multimodal reasoning, their long-context inference remains prohibitively expensive due to the massive computation and memory overhead of visual Key-Value (KV) caches. Existing KV compression methods often apply uniform pruning across visual tokens and layers, leading to substantial information loss and degraded performance.To address this challenge, we propose VisCache, a plug-and-play framework for coarse-to-fine Visual KV Cache pruning without training, which consists of two synergistic stages. First, a lightweight VLM filters temporal redundancy by selectively forwarding semantically informative keyframes. Second, we introduce {PruneKV}, a surgical KV compression algorithm tailored to the attention dynamics of VLLMs. Unlike rigid pruning strategies, PruneKV adopts a parabolic layer-wise budget allocation together with an asymmetric update mechanism that selectively prunes keys while fusing values, thereby preserving critical contextual information. Extensive experiments demonstrate that VisCache substantially improves inference efficiency, achieving up to {2.35×\times speedup} and significant memory reduction while maintaining competitive performance with only {19--28%} KV cache retention. VisCache consistently outperforms existing baselines, establishing a new Pareto frontier between efficiency and performance for long-context VLLM inference. Code is available at https://github.com/Wlklk/VisCache