← Back to all news
arXiv Computer Vision By Yuheng Shi, Xiaohuan Pei, Minjing Dong, Chang Xu

Region-Level Policy Optimization for Fine-grained MLLM Perception

Read the original on arXiv Computer Vision →

The paper introduces Vision‑RL2, a region‑level reinforcement learning approach that optimizes a lightweight proposal network for fine‑grained multimodal large language model (MLLM) perception. By treating coherent image regions as actions and scoring them with a frozen MLLM reader, the method selectively focuses visual resolution on evidence, reducing token usage while improving accuracy across multiple benchmarks and backbones. The approach eliminates the need for region annotations, response sampling, or reasoning trajectories, and the refined proposals enable sparse encoding that magnifies relevant evidence.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv Computer Vision
Sep 1

State-Conditioned Visual Evidence Retrieval for Fine-Grained Perception in Document Vision-Language Models

arXiv:2608.28698v1 Announce Type: new Abstract: Compared with typical vision-language tasks, document parsing places stronger demands on fine-grained visual perception. Existing vision-language model...

By Mingxu Chai, Chenyu Liu, Ziyu Shen, Jiazheng Zhang, Kaidi Zhang, Ruoyu Chen, Jun Long, Jihua Kang, Tao Gui, Qi Zhang
llmsmultimodalbenchmarks
More like this →
arXiv Computer Vision
Oct 16

Perception or Reasoning? Diagnosing and Tackling Reinforcement Learning Bottlenecks in VLMs

The paper introduces Perception and Reasoning Attribution (PARA), a method that quantifies how much of a vision‑language model’s errors can be fixed by better perception versus stronger reasoning. PARA reveals that reinforcement learning (RL) benefits more from improving reasoning than perception, and motivates a new group‑relative attention distillation objective called GRAD. GRAD directly guides weaker rollouts toward the visual attention patterns of the best rollouts, consistently boosting performance across multiple model scales and benchmarks.

By Zeyuan Yang, Zhuohao Chen, Jiaben Chen, Yao Zhang, Maohao Shen, Chuang Gan
llmsreinforcement-learningefficiencymultimodalbenchmarks
More like this →