tongjingqi / Thinking-with-VideoLinks
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.
☆236Updated 3 weeks ago
Alternatives and similar repositories for Thinking-with-Video
Users that are interested in Thinking-with-Video are comparing it to the libraries listed below
Sorting:
- The official repository for the paper "ThinkMorph: Emergent Properties in Multimodal Interleaved Chain-of-Thought Reasoning"☆140Updated 3 weeks ago
- Thinking with Videos from Open-Source Priors. We reproduce chain-of-frames visual reasoning by fine-tuning open-source video models. Give…☆206Updated 3 months ago
- Official Code for "ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoning"☆79Updated last month
- Incentivizing "Thinking with Long Videos" via Native Tool Calling☆183Updated this week
- Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens (arXiv 2025)☆233Updated 5 months ago
- https://huggingface.co/datasets/multimodal-reasoning-lab/Zebra-CoT☆117Updated 2 months ago
- TiViBench: Benchmarking Think-in-Video Reasoning for Video Generative Models☆64Updated 2 months ago
- [NeurIPS 2025] Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing☆90Updated 6 months ago
- A framework for unified personalized model, achieving mutual enhancement between personalized understanding and generation. Demonstrating…☆128Updated last month
- ☆59Updated 5 months ago
- A collection of awesome think with videos papers.☆83Updated last month
- Doodling our way to AGI ✏️ 🖼️ 🧠☆120Updated 8 months ago
- ☆308Updated last month
- Pixel-Level Reasoning Model trained with RL [NeuIPS25]☆267Updated 2 months ago
- Data and Code for CVPR 2025 paper "MMVU: Measuring Expert-Level Multi-Discipline Video Understanding"☆78Updated 11 months ago
- ☆168Updated 2 months ago
- [AAAI 2026] GenMAC for Compositional Text-to-Video Generation☆31Updated 3 weeks ago
- Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?☆86Updated 6 months ago
- [ICLR 2026] Uni-CoT: Towards Unified Chain-of-Thought Reasoning Across Text and Vision☆205Updated this week
- The official code of "VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning" [NeurIPS25]☆179Updated 7 months ago
- Code for MetaMorph Multimodal Understanding and Generation via Instruction Tuning☆232Updated last week
- Interleaving Reasoning: Next-Generation Reasoning Systems for AGI☆240Updated 3 months ago
- Official Code for "Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search"☆394Updated 4 months ago
- A Collection of Papers on Diffusion Language Models☆152Updated 4 months ago
- Visual Planning: Let's Think Only with Images☆294Updated 8 months ago
- ☆114Updated 6 months ago
- MetaSpatial leverages reinforcement learning to enhance 3D spatial reasoning in vision-language models (VLMs), enabling more structured, …☆201Updated 8 months ago
- Official repository for "Visual Generation Unlocks Human-Like Reasoning through Multimodal World Models", https://arxiv.org/abs/2601.1983…☆48Updated this week
- TokLIP: Marry Visual Tokens to CLIP for Multimodal Comprehension and Generation☆235Updated 5 months ago
- Official release of "Spatial-SSRL: Enhancing Spatial Understanding via Self-Supervised Reinforcement Learning"☆108Updated last month