Region-Level Policy Optimization for Fine-grained MLLM Perception

Papers

arxiv:2609.19745

Published on Sep 17

· Submitted by

Yuheng Shi on Sep 18

Upvote

Authors:

Yuheng Shi ,

Abstract

Fine-grained visual perception in MLLMs is commonly improved by raising the resolution, but the added visual tokens inflate vision-encoding and language-model prefilling costs. We show that the two operations underlying fine-grained perception, localizing the region of interest (RoI) and recognizing its content, have different resolution requirements. In a controlled diagnostic, localization tolerates roughly 3 to 4 times stronger token compression than recognition, which motivates localizing from a coarse view and concentrating resolution on the selected evidence. Decoding coordinates with the MLLM can be trained end-to-end from answers, but costs a full model pass per query and depends on grounding ability. A lightweight proposal network distilled from the model's attention is fast, but inherits the noise of its attention targets. The RoI from the proposal network reaches the answer through a discrete region choice, so its faithfulness to the answer cannot supervise the network. We therefore optimize the proposal network with region-level reinforcement learning, which we call Vision-RL2. It treats coherent regions as actions, and a frozen MLLM reader scores each one by how its removal changes the answer likelihood. Complementary subtractive and additive objectives suppress distracting proposals and recover missing evidence, updating only the predictor without region annotations, response sampling, or reasoning trajectories. The refined proposal further enables a sparse encoding that magnifies evidence and excludes background tokens. Across six fine-grained benchmarks and four MLLM backbones, Vision-RL2 improves accuracy over the base model at every token budget and surpasses its largest-budget accuracy with about 4 times fewer visual tokens. Code is available at https://github.com/YuHengsss/VisionRL2 .

View arXiv page View PDF Project page GitHub 5 Add to collection

Community

YuhengSSS

Paper author Paper submitter 5 days ago

Vision-RL²: Region-Level Policy Optimization for Fine-grained MLLM Perception

Fine-grained perception in MLLMs usually means raising the resolution, which inflates visual-token and prefill cost. We show that localizing the region of interest tolerates roughly 3–4× stronger token compression than recognizing its content, so the two should not share one resolution.

Vision-RL² trains a lightweight region proposal network on top of a frozen MLLM with region-level RL: coherent regions are the actions, and a frozen reader scores each one by how much its removal changes the answer likelihood. No region annotations, no response sampling, no reasoning traces. The refined proposal also enables a sparse visual encoding that keeps only foreground tokens.

Across six fine-grained benchmarks (V*, ZoomBench, HR-Bench 4K/8K, MME-RealWorld EN/CN) and four backbones (Qwen3.5-4B/9B, Qwen2.5-VL-7B, and the encoder-free Gemma-4-12B), Vision-RL² improves over the base model at every visual-token budget, and outperforms prior methods that fully fine-tune the model while training an order of magnitude fewer parameters.

Code: https://github.com/YuHengsss/VisionRL2
Checkpoints for all four backbones + training data: https://hf-mirror.com/collections/YuhengSSS/visionrl2
Project page with an interactive walkthrough of one training step on real samples: https://yuhengsss.github.io/VisionRL2/

librarian-bot

4 days ago

This is an automated message from the Librarian Bot. I found the following papers similar to this paper.

The following papers were recommended by the Semantic Scholar API

Please give a thumbs up to this comment if you found it helpful!

If you want recommendations for any Paper on HF Mirror checkout this Space

You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment

Upvote

Get this paper in your agent:

hf papers read 2609.19745

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 4

Datasets citing this paper 1

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2609.19745 in a Space README.md to link it from this page.

Abstract

Community

Models citing this paper 4

Datasets citing this paper 1

Spaces citing this paper 0

Collections including this paper 1

相关阅读