cs.CVNov 16, 2026

ReAccess: Look Once, Stay Focused with Efficient Test Time Memory

Authors: Tianhao Chen, Yilong Fan, Yuheng Wu, Xiaobin Hu, Dongman Lee

Organizations: KAIST · Tianjin University · National University of Singapore

Abstract

Despite recent advances, vision-language models (VLMs) still struggle with fine-grained visual understanding, often failing to effectively utilize critical evidence already encoded in their visual representations. Existing approaches address this limitation through repeated visual processing or explicit reasoning, introducing substantial computational overhead. In this paper, we propose ReAccess, a lightweight framework that preserves and reuses question-relevant visual evidence through compact associative memory. Constructed during a single visual prefill, the memory supports progressive evidence retrieval that steers both attention queries and hidden representations, enabling effective visual grounding without repeated image encoding or explicit reasoning traces. Extensive experiments demonstrate consistent improvements in both general visual understanding and fine-grained perception, while achieving substantially faster inference than existing reasoning-intensive approaches, demonstrating a promising path to efficient multimodal reasoning.

Figures & tables

Explore similar work

CardsList
  1. LookWise: Knowing When and Where to Look for Fine-Grained Visual Reasoning in Multimodal Large Language Models

    Feb 26, 2026Yuxiang Shen, Hailong Huang, Zhenkun Gao +6VLM ReasoningLarge Vision-Language Models

  2. Improving Visual Reasoning with Iterative Evidence Refinement

    Mar 14, 2026Zeru Shi, Kai Mei, Yihao Quan +2VLM ReasoningVisually Grounded Reasoning