We introduce 'Thinking with Video', a new paradigm leveraging video generation for multimodal reasoning. Our VideoThinkBench shows that Sora-2 surpasses GPT5 by 10% on eyeballing puzzles and reaches 69% accuracy on MMMU.

Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens (arXiv 2025)

Official code for NeurIPS 2025 paper "GRIT: Teaching MLLMs to Think with Images"

A Comprehensive Survey on Evaluating Reasoning Capabilities in Multimodal Large Language Models.

Rui Qian, Xin Yin, Dejing Dou†: Reasoning to Attend: Try to Understand How <SEG> Token Works (CVPR 2025)

[NeurIPS 2025] Official implementation for the paper "SeePhys: Does Seeing Help Thinking? -- Benchmarking Vision-Based Physics Reasoning"

Latest Advances on (RL based) Multimodal Reasoning and Generation in Multimodal Large Language Models

Generative Universal Verifier as Multimodal Meta-Reasoner

WeThink: Toward General-purpose Vision-Language Reasoning via Reinforcement Learning

🌴 ARES is an open-source framework for adaptive multimodal reasoning, featuring a two-stage pipeline—Adaptive Cold-Start and Entropy-Shaped Policy Optimization—to balance reasoning depth and efficiency.

A step-by-step reasoning framework for 3D scene understanding

Code and dataset for TurtleBench: A Visual Programming Benchmark in Turtle Geometry

Project COLON-X (Shaping the neXt frontier in intelligent COLONoscopy)

Welcome to the 🤖 Generative AI 🤖 Papers Repository! This repository is dedicated to compiling and sharing research papers that are trending ✨/ impactful 💥in the domain of Generative AI. This compilation in part motivated by the course CSE 598: Topics in Generative AI by Dr. Yezhou Yang, Arizona State University.

🎥 Generate videos with advanced multimodal reasoning to enhance understanding and interaction, pushing the boundaries of video content creation.