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

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

    Nov 11, 2026Ke Li, Zishan Shao, Yiran ChenKV-Cache CompressionEfficient VLM Inference

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

    Aug 25, 2026Lyuke Wang, Zhuo Li, Guangxu ZhuEfficient VLM InferenceLong-Context VLMs