arXiv · 2611.20936
ReAccess: Look Once, Stay Focused with Efficient Test Time Memory
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.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Tianhao Chen, Yilong Fan, Yuheng Wu, Xiaobin Hu, Dongman Lee. 2026-11-16. ReAccess: Look Once, Stay Focused with Efficient Test Time Memory. https://searcharxiv.com/abs/2611.20936
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.