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.
☆225Updated this week
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:
- Thinking with Videos from Open-Source Priors. We reproduce chain-of-frames visual reasoning by fine-tuning open-source video models. Give…☆193Updated 2 months ago
- The official repository for the paper "ThinkMorph: Emergent Properties in Multimodal Interleaved Chain-of-Thought Reasoning"☆122Updated 3 weeks ago
- Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens (arXiv 2025)☆207Updated 4 months ago
- TiViBench: Benchmarking Think-in-Video Reasoning for Video Generative Models☆62Updated 3 weeks ago
- Official Code for "ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoning"☆72Updated 2 weeks ago
- Incentivizing "Thinking with Long Videos" via Native Tool Calling☆142Updated this week
- Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing☆84Updated 4 months ago
- ☆297Updated 2 months ago
- Uni-CoT: Towards Unified Chain-of-Thought Reasoning Across Text and Vision☆184Updated this week
- ☆152Updated 3 weeks ago
- Interleaving Reasoning: Next-Generation Reasoning Systems for AGI☆220Updated 2 months ago
- A framework for unified personalized model, achieving mutual enhancement between personalized understanding and generation. Demonstrating…☆127Updated 2 months ago
- ☆55Updated 3 months ago
- Official release of "Spatial-SSRL: Enhancing Spatial Understanding via Self-Supervised Reinforcement Learning"☆91Updated 3 weeks ago
- A Collection of Papers on Diffusion Language Models☆149Updated 3 months ago
- https://huggingface.co/datasets/multimodal-reasoning-lab/Zebra-CoT☆108Updated last month
- A collection of awesome think with videos papers.☆73Updated 2 weeks ago
- ☆30Updated last year
- Data and Code for CVPR 2025 paper "MMVU: Measuring Expert-Level Multi-Discipline Video Understanding"☆76Updated 9 months ago
- Cambrian-S: Towards Spatial Supersensing in Video☆429Updated this week
- The official code of "VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning" [NeurIPS25]☆169Updated 6 months ago
- Doodling our way to AGI ✏️ 🖼️ 🧠☆118Updated 6 months ago
- ☆111Updated 4 months ago
- (NeurIPS 2025 D&B Track) OverLayBench: A Benchmark for Layout-to-Image Generation with Dense Overlaps☆23Updated last month
- Visual Planning: Let's Think Only with Images☆285Updated 7 months ago
- Official Code for "Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search"☆377Updated 3 months ago
- Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?☆81Updated 5 months ago
- ✈️ [ICCV 2025] Towards Stabilized and Efficient Diffusion Transformers through Long-Skip-Connections with Spectral Constraints☆78Updated 5 months ago
- ☆95Updated 5 months ago
- ☆32Updated 4 months ago