conftrace_

visual anchoring

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

token compression (2) multimodal large language model (2) collaborative decoding (1) chain-of-thought reasoning (1) visual question answering (1) information bottleneck (1)

Papers

Chain-of-Thought Compression Should Not Be Blind: V-Skip for Efficient Multimodal Reasoning via Dual-Path Anchoring ACL 2026 AVAM: a Universal Training-free Adaptive Visual Anchoring Embedded into Multimodal Large Language Model for Multi-image Question Answering ICCV 2025