arXiv Computation and Language
Reward Design for Physical Reasoning in Vision-Language Models
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
arXiv AI
Jun 16
Thinking with Visual Grounding
arXiv:2606. 16122v1 Announce Type: new Abstract: Visual thinking should not only sound right; it should show its evidence.
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.
arXiv AI
Jul 8
Bridging Physical Reasoning and Task Generalization via Visual Action Outcome Reasoning Alignment
arXiv:2607. 06522v1 Announce Type: new Abstract: Vision-language models (VLMs) struggle to generalize in interactive physical reasoning, particularly under unseen tasks and environments.
arXiv AI
Jun 19
Vero: An Open RL Recipe for General Visual Reasoning
arXiv:2604. 04917v3 Announce Type: replace-cross Abstract: What does it take to build a visual reasoner that works across charts, science, spatial understanding, and open-ended tasks?
arXiv AI
Jul 7
SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards
arXiv:2511. 07403v2 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) have achieved remarkable progress in vision-language tasks, but continue to struggle with spatial reasoning.
arXiv Computer Vision
3d ago
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.