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.
☆298Mar 21, 2026Updated last month
Alternatives and similar repositories for Thinking-with-Video
Users that are interested in Thinking-with-Video are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A curated list of awesome resources about reward construction for AI agents. This repository covers cutting-edge research, and practical …☆59Sep 1, 2025Updated 8 months ago
- VehicleWorld is the first comprehensive multi-device environment for intelligent vehicle interaction that accurately models the complex, …☆22Sep 16, 2025Updated 8 months ago
- UnifiedToolHub is a comprehensive project supporting LLM-based tool use, designed to unify various tool-use dataset formats and provide t…☆21Jul 23, 2025Updated 9 months ago
- [ACL 2025] "World Modeling Makes a Better Planner: Dual Preference Optimization for Embodied Task Planning." https://arxiv.org/abs/2503.1…☆18Jul 22, 2025Updated 9 months ago
- Thinking with Videos from Open-Source Priors. We reproduce chain-of-frames visual reasoning by fine-tuning open-source video models. Give…☆227Apr 13, 2026Updated last month
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- [ICLR 2026] Official repo for "Spotlight on Token Perception for Multimodal Reinforcement Learning"☆62Apr 3, 2026Updated last month
- [CVPR 2026] An official implementation of "Think Visually, Reason Textually: Vision-Language Synergy in ARC"☆41Nov 26, 2025Updated 5 months ago
- Use the tokenizer in parallel to achieve superior acceleration☆20Mar 21, 2024Updated 2 years ago
- Official repository for "Visual Generation Unlocks Human-Like Reasoning through Multimodal World Models", https://arxiv.org/abs/2601.1983…☆92Mar 9, 2026Updated 2 months ago
- An open-source personal academic homepage template characterized by its user-friendly design and extensive scalability.☆37Oct 6, 2025Updated 7 months ago
- [CVPR 2026] Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens☆274Aug 2, 2025Updated 9 months ago
- Rethinking the Trust Region in LLM Reinforcement Learning☆54Mar 2, 2026Updated 2 months ago
- ☆66May 7, 2026Updated last week
- Game-RL: Synthesizing Multimodal Verifiable Game Data to Boost VLMs' General Reasoning☆153May 13, 2026Updated last week
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Are Video Models Ready as Zero-shot Reasoners?☆87Nov 24, 2025Updated 5 months ago
- [CVPR 2026] Official Code for "ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoning"☆189Feb 13, 2026Updated 3 months ago
- [ICML 2025] M-STAR (Multimodal Self-Evolving TrAining for Reasoning) Project. Diving into Self-Evolving Training for Multimodal Reasoning☆74Jul 13, 2025Updated 10 months ago
- [ICML'26] VideoGPA is a self-supervised framework that enhances 3D consistency in Video Diffusion Models.☆54May 9, 2026Updated last week
- https://huggingface.co/datasets/multimodal-reasoning-lab/Zebra-CoT☆134Jan 30, 2026Updated 3 months ago
- [ICLR 2026 Oral] Generative Universal Verifier as Multimodal Meta-Reasoner☆58Nov 14, 2025Updated 6 months ago
- Official PyTorch implementation of paper “InsViE-1M: Effective Instruction-based Video Editing with Elaborate Dataset Construction”☆34Apr 3, 2026Updated last month
- [ICLR 2026] The official repository for paper "ThinkMorph: Emergent Properties in Multimodal Interleaved Chain-of-Thought Reasoning"☆184May 1, 2026Updated 2 weeks ago
- Codes for the paper "BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping…☆93Jan 29, 2026Updated 3 months ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- [ACL 2026 Findings, ICCV 2025 Workshop Outstanding Paper Award] VChain: Chain-of-Visual-Thought for Reasoning in Video Generation☆119Apr 8, 2026Updated last month
- [KernelGYM & Dr. Kernel] A distributed GPU environment and a collection of RL training methods to support RL for Kernel Generations [ICML…☆172Mar 29, 2026Updated last month
- Official repo for: Epipolar Geometry Improves Video Generation Models☆91Oct 28, 2025Updated 6 months ago
- ComfyUI version of WithAnyone☆24Dec 18, 2025Updated 5 months ago
- [CVPR' 25] Official repo for From Head to Tail: Towards Balanced Representation in Large Vision-Language Models through Adaptive Data Cal…☆22Jun 6, 2025Updated 11 months ago
- [CVPR 2025] Adaptive Keyframe Sampling for Long Video Understanding☆210Dec 19, 2025Updated 5 months ago
- ☆159Mar 30, 2026Updated last month
- [ICLR26] Beyond Real: Imaginary Extension of Rotary Position Embeddings for Long-Context LLMs☆33Dec 9, 2025Updated 5 months ago
- [CVPR2026] VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice☆85Feb 27, 2026Updated 2 months ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- ☆35Feb 18, 2026Updated 3 months ago
- [ICLR2026] Laser: Learn to Reason Efficiently with Adaptive Length-based Reward Shaping☆65May 22, 2025Updated 11 months ago
- [Arxiv 2025] Official PyTorch Implementation of "SVG-T2I: Scaling up Text-to-Image Latent Diffusion Model Without Variational Autoencoder…☆150Dec 18, 2025Updated 5 months ago
- In this work, we investigate the compositionality of large language models (LLMs) in mathematical reasoning. Specifically, we construct a…☆60Mar 15, 2025Updated last year
- MOVA: Towards Scalable and Synchronized Video–Audio Generation☆996May 6, 2026Updated 2 weeks ago
- Official eval code for ROVER: Benchmarking Reciprocal Cross-Modal Reasoning for Omnimodal Generation☆27Dec 12, 2025Updated 5 months ago
- Official code for "Rethinking Chain-of-Thought Reasoning for Videos"☆20Dec 14, 2025Updated 5 months ago