MMODELYST
Papers/DyCo-RL: Dynamic Cross-Modal Coordination for Visual Reasoning
PAP

DyCo-RL: Dynamic Cross-Modal Coordination for Visual Reasoning

Jun 6, 2026

arXiv
Abstract

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a leading paradigm for enhancing visual reasoning in Multimodal Large Language Models (MLLMs). However, existing RLVR methods optimize primarily for the reasoning outcome, fundamentally overlooking the fine-grained cross-modal coordination required during the generation process. Through token-level analyses and controlled interventions, we reveal that during Chain-of-Thought (CoT) reasoning, MLLMs frequently fail to dynamically alternate between extracting visual evidence and synthesizing textual context-a coordination breakdown that is causally linked to reasoning failures. Motivated by these findings, we propose DyCo-RL, which integrates dynamic cross-modal coordination into RLVR optimization. Specifically, DyCo-RL uses the Fisher-Rao geodesic distance to measure within-modality attention shifts, assigning tokens to either visually-oriented or text-oriented functional roles. It then evaluates the alignment between a token's actual attention allocation and its assigned role, leveraging this score for alignment-guided advantage reweighting during policy optimization. Extensive experiments demonstrate that the algorithm-agnostic DyCo-RL, when applied to Qwen2.5-VL-3B/7B, consistently improves four representative RLVR algorithms across seven benchmarks spanning visual-centric and mathematical reasoning.

Select text to highlight · click a highlight to remove · saved in this browser only
Authors
Hangui Lin, Yan Shu, Zhengyang Liang, Chi Liu, Xiangrui Liu, Minghao Qin, Teng Long, Zheng Liu, Nicu Sebe
Your notes (browser-local)
saved
Cross-links
No linked entities.
arXiv:2606.08035