Top papers
- VisDoT : Enhancing Visual Reasoning through Human-Like Interpretation Grounding and Decomposition of Thought(8.0)
- CodePercept: Code-Grounded Visual STEM Perception for MLLMs(8.0)
- Through the Lens of Contrast: Self-Improving Visual Reasoning in VLMs(7.0)
- MM-CondChain: A Programmatically Verified Benchmark for Visually Grounded Deep Compositional Reasoning(4.0)