Vision-Matters
Collection
13 items • Updated • 2
Vision Matters: Simple Visual Perturbations Can Boost Multimodal Math Reasoning
Paper Title and Link
The model was presented in the paper Vision Matters: Simple Visual Perturbations Can Boost Multimodal Math Reasoning. You can also find the paper on arXiv: Vision Matters: Simple Visual Perturbations Can Boost Multimodal Math Reasoning (arXiv:2506.09736)
Paper Abstract
Vision-Matters is a simple visual perturbation framework that can be easily integrated into existing post-training pipelines including SFT, DPO, and GRPO. Our findings highlight the critical role of visual perturbation: better reasoning begins with better seeing.
- 🐙 GitHub Repo: YutingLi0606/Vision-Matters
- 💾 Dataset: Yuting6/vision-matters on Hugging Face
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for Yuting6/Vision-Matters-Evaluation
Base model
Qwen/Qwen2.5-VL-7B-Instruct