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.
☆291Mar 21, 2026Updated 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. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- VehicleWorld is the first comprehensive multi-device environment for intelligent vehicle interaction that accurately models the complex, …☆21Sep 16, 2025Updated 7 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 8 months ago
- [CVPR 2026] FluxMem: Adaptive Hierarchical Memory for Streaming Video Understanding☆54Mar 16, 2026Updated last month
- [ACL 2025] "World Modeling Makes a Better Planner: Dual Preference Optimization for Embodied Task Planning." https://arxiv.org/abs/2503.1…☆18Jul 22, 2025Updated 8 months ago
- We propose Reinforcement Learning from Community Feedback (RLCF), a training paradigm that uses large-scale community signals as supervis…☆391Mar 29, 2026Updated 3 weeks ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Thinking with Videos from Open-Source Priors. We reproduce chain-of-frames visual reasoning by fine-tuning open-source video models. Give…☆223Apr 13, 2026Updated last week
- [ICLR 2026] Official repo for "Spotlight on Token Perception for Multimodal Reinforcement Learning"☆55Apr 3, 2026Updated 2 weeks 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…☆87Mar 9, 2026Updated last month
- [ICCV'25] ScenePainter: Semantically Consistent Perpetual 3D Scene Generation with Concept Relation Alignment☆37Oct 5, 2025Updated 6 months ago
- An open-source personal academic homepage template characterized by its user-friendly design and extensive scalability.☆37Oct 6, 2025Updated 6 months ago
- Rethinking the Trust Region in LLM Reinforcement Learning☆52Mar 2, 2026Updated last month
- ☆65Updated this week
- Game-RL: Synthesizing Multimodal Verifiable Game Data to Boost VLMs' General Reasoning☆149Updated this 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?☆86Nov 24, 2025Updated 4 months ago
- ☆24Jul 20, 2025Updated 9 months ago
- [CVPR 2026] Official Code for "ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoning"☆186Feb 13, 2026Updated 2 months ago
- 复旦研究生入学教育测试☆24Aug 28, 2025Updated 7 months ago
- ☆26Oct 11, 2025Updated 6 months ago
- VideoGPA is a self-supervised framework that enhances 3D consistency in Video Diffusion Models.☆50Updated this week
- [CVPR 2026] Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens☆266Aug 2, 2025Updated 8 months ago
- [ICLR 2026 Oral] Generative Universal Verifier as Multimodal Meta-Reasoner☆56Nov 14, 2025Updated 5 months ago
- https://huggingface.co/datasets/multimodal-reasoning-lab/Zebra-CoT☆132Jan 30, 2026Updated 2 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Official PyTorch implementation of paper “InsViE-1M: Effective Instruction-based Video Editing with Elaborate Dataset Construction”☆33Apr 3, 2026Updated 2 weeks ago
- MOSS-Audio-Tokenizer is a Causal Transformer-based audio tokenizer built on the CAT architecture. Trained on 3M hours of diverse audio, i…☆191Apr 13, 2026Updated last week
- [KernelGYM & Dr. Kernel] A distributed GPU environment and a collection of RL training methods to support RL for Kernel Generations☆156Mar 29, 2026Updated 3 weeks ago
- [ICLR 2026] The official repository for paper "ThinkMorph: Emergent Properties in Multimodal Interleaved Chain-of-Thought Reasoning"☆178Jan 26, 2026Updated 2 months ago
- [ACL 2026 Findings, ICCV 2025 Workshop Outstanding Paper Award] VChain: Chain-of-Visual-Thought for Reasoning in Video Generation☆118Apr 8, 2026Updated last week
- Beyond Real: Imaginary Extension of Rotary Position Embeddings for Long-Context LLMs☆33Dec 9, 2025Updated 4 months ago
- ComfyUI version of WithAnyone☆24Dec 18, 2025Updated 4 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 10 months ago
- [CVPR2026] VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice☆83Feb 27, 2026Updated last month
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- [CVPR 2025] Adaptive Keyframe Sampling for Long Video Understanding☆202Dec 19, 2025Updated 4 months ago
- ☆158Mar 30, 2026Updated 3 weeks ago
- Complex-Edit: CoT-Like Instruction Generation for Complexity-Controllable Image Editing Benchmark☆28Apr 22, 2025Updated 11 months ago
- ☆33Feb 18, 2026Updated 2 months ago
- [ICLR2026] Laser: Learn to Reason Efficiently with Adaptive Length-based Reward Shaping☆63May 22, 2025Updated 10 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
- [CVPR 2026] Video-as-Answer: Predict and Generate Next Video Event with Joint-GRPO☆107Feb 28, 2026Updated last month