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.
☆199Updated last 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:
- Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens (arXiv 2025)☆194Updated 3 months ago
- Thinking with Videos from Open-Source Priors. We reproduce chain-of-frames visual reasoning by fine-tuning open-source video models. Give…☆185Updated last month
- The official repository for the paper "ThinkMorph: Emergent Properties in Multimodal Interleaved Chain-of-Thought Reasoning"☆111Updated last week
- ☆283Updated last month
- Official release of "Spatial-SSRL: Enhancing Spatial Understanding via Self-Supervised Reinforcement Learning"☆75Updated this week
- A Collection of Papers on Diffusion Language Models☆145Updated 2 months ago
- ☆55Updated 3 months ago
- Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing☆79Updated 4 months ago
- TiViBench: Benchmarking Think-in-Video Reasoning for Video Generative Models☆60Updated last week
- ☆134Updated last week
- Code for MetaMorph Multimodal Understanding and Generation via Instruction Tuning☆222Updated 7 months ago
- TokLIP: Marry Visual Tokens to CLIP for Multimodal Comprehension and Generation☆231Updated 3 months ago
- https://huggingface.co/datasets/multimodal-reasoning-lab/Zebra-CoT☆103Updated 3 weeks ago
- 📖 This is a repository for organizing papers, codes, and other resources related to unified multimodal models.☆331Updated last month
- Uni-CoT: Towards Unified Chain-of-Thought Reasoning Across Text and Vision☆170Updated 2 weeks ago
- Interleaving Reasoning: Next-Generation Reasoning Systems for AGI☆205Updated last month
- Doodling our way to AGI ✏️ 🖼️ 🧠☆113Updated 6 months ago
- ✈️ [ICCV 2025] Towards Stabilized and Efficient Diffusion Transformers through Long-Skip-Connections with Spectral Constraints☆76Updated 4 months ago
- Data and Code for CVPR 2025 paper "MMVU: Measuring Expert-Level Multi-Discipline Video Understanding"☆75Updated 9 months ago
- ☆30Updated 11 months ago
- Official repo of paper "Reconstruction Alignment Improves Unified Multimodal Models". Unlocking the Massive Zero-shot Potential in Unifie…☆312Updated last month
- Official Implementation of LaViDa: :A Large Diffusion Language Model for Multimodal Understanding☆171Updated last month
- The official code of "VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning" [NeurIPS25]☆166Updated 5 months ago
- A tiny paper rating web☆38Updated 8 months ago
- Official repository of 'ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing’☆57Updated 5 months ago
- A framework for unified personalized model, achieving mutual enhancement between personalized understanding and generation. Demonstrating…☆124Updated last month
- [NeurIPS 2025] MINT-CoT: Enabling Interleaved Visual Tokens in Mathematical Chain-of-Thought Reasoning☆88Updated 2 months ago
- (NeurIPS 2025 D&B Track) OverLayBench: A Benchmark for Layout-to-Image Generation with Dense Overlaps☆23Updated 2 weeks ago
- TraceRL & TraDo-8B: Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models☆327Updated last week
- WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation☆163Updated 3 weeks ago