← Back to all news
arXiv Computer Vision By Zeyuan Yang, Zhuohao Chen, Jiaben Chen, Yao Zhang, Maohao Shen, Chuang Gan

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

Read the original on arXiv Computer Vision →

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.

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 Computation and Language
Sep 4

Attend to Evidence: Evidence-Anchored Spatial Attention Supervision for Multimodal RLVR

The paper introduces EASE, a method that enhances multimodal reinforcement learning with verifiable rewards (RLVR) by adding visual‑evidence process supervision. EASE transforms annotated evidence regions into smoothed visual‑token targets and uses them to guide attention during RL training, but only on high‑reward trajectories. Experiments on Qwen2.5‑VL‑7B, Qwen3‑VL‑4B, and Qwen3‑VL‑8B show that EASE improves average scores over DAPO by 2.5 to 3.1 points across perception, hallucination, visual math, and multimodal reasoning benchmarks, and diagnostics confirm better alignment of visual attention with annotated evidence.

By Ruina Hu, Chen Wang, Lai Wei, Jionghao Bai, Bin Yu, Weiran Huang, Kai Wang, Yue Wang
llmsreinforcement-learningmultimodalbenchmarkssafety
More like this →
arXiv Computation and Language
Sep 3

On Asymmetric Optimization of Reasoning and Perception in Vision-Language Model Post-Training

The paper investigates why post‑training boosts reasoning more than perception in vision‑language models. Using a diagnostic framework with synthetic tasks, it finds a perception‑reasoning asymmetry: supervised fine‑tuning suffers from token imbalance, while reinforcement learning suffers from reward coupling. The authors propose reweighting losses and perception‑aware rewards, achieving up to 18.2‑point and 6.0‑point gains respectively, and show that these methods also improve real‑world visual reasoning by up to 3.3 points.

By Xueqing Wu, Yu-Chi Lin, Kai-Wei Chang, Nanyun Peng
llmsreinforcement-learningfine-tuningmultimodalbenchmarks
More like this →