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.
☆270Feb 21, 2026Updated 2 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:
- A curated list of awesome resources about reward construction for AI agents. This repository covers cutting-edge research, and practical …☆55Sep 1, 2025Updated 6 months ago
- VehicleWorld is the first comprehensive multi-device environment for intelligent vehicle interaction that accurately models the complex, …☆21Sep 16, 2025Updated 5 months ago
- [ACL 2025] "World Modeling Makes a Better Planner: Dual Preference Optimization for Embodied Task Planning." https://arxiv.org/abs/2503.1…☆17Jul 22, 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…☆19Jul 23, 2025Updated 7 months ago
- Thinking with Videos from Open-Source Priors. We reproduce chain-of-frames visual reasoning by fine-tuning open-source video models. Give…☆214Oct 12, 2025Updated 4 months ago
- [CVPR 2026] An official implementation of "Think Visually, Reason Textually: Vision-Language Synergy in ARC"☆37Nov 26, 2025Updated 3 months ago
- [ICLR 2026] Official repo for "Spotlight on Token Perception for Multimodal Reinforcement Learning"☆49Jan 30, 2026Updated last month
- VideoGPA is a self-supervised framework that enhances 3D consistency in Video Diffusion Models.☆37Feb 3, 2026Updated last month
- Rethinking the Trust Region in LLM Reinforcement Learning☆39Feb 25, 2026Updated last week
- Use the tokenizer in parallel to achieve superior acceleration☆20Mar 21, 2024Updated last year
- [ICCV'25] ScenePainter: Semantically Consistent Perpetual 3D Scene Generation with Concept Relation Alignment☆36Oct 5, 2025Updated 5 months ago
- [ICLR 2026 Oral] Generative Universal Verifier as Multimodal Meta-Reasoner☆52Nov 14, 2025Updated 3 months ago
- [ICML 2025] M-STAR (Multimodal Self-Evolving TrAining for Reasoning) Project. Diving into Self-Evolving Training for Multimodal Reasoning☆71Jul 13, 2025Updated 7 months ago
- StableWorld: Towards Stable and Consistent Long Interactive Video Generation☆81Feb 3, 2026Updated last month
- [CVPR 2026] Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens☆246Aug 2, 2025Updated 7 months ago
- Official repository for "Visual Generation Unlocks Human-Like Reasoning through Multimodal World Models", https://arxiv.org/abs/2601.1983…☆78Feb 13, 2026Updated 3 weeks ago
- Game-RL: Synthesizing Multimodal Verifiable Game Data to Boost VLMs' General Reasoning☆136Updated this week
- [ICCV 2025 Workshop Outstanding Paper Award] VChain: Chain-of-Visual-Thought for Reasoning in Video Generation☆115Oct 7, 2025Updated 5 months ago
- 复旦研究生入学教育测试☆23Aug 28, 2025Updated 6 months ago
- [CVPR 2026] Official Code for "ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoning"☆84Feb 13, 2026Updated 3 weeks ago
- Are Video Models Ready as Zero-shot Reasoners?☆84Nov 24, 2025Updated 3 months ago
- [CVPR 2026] Video-as-Answer: Predict and Generate Next Video Event with Joint-GRPO☆96Feb 28, 2026Updated last week
- [ICLR 2026] OmniSpatial: Towards Comprehensive Spatial Reasoning Benchmark for Vision Language Models☆80Jan 21, 2026Updated last month
- https://huggingface.co/datasets/multimodal-reasoning-lab/Zebra-CoT☆125Jan 30, 2026Updated last month
- Complex-Edit: CoT-Like Instruction Generation for Complexity-Controllable Image Editing Benchmark☆28Apr 22, 2025Updated 10 months ago
- CVPR 2025 Accepted Papers☆24Dec 20, 2025Updated 2 months ago
- [NIPS 2025] FreqPolicy: Frequency Autoregressive Visuomotor Policy with Continuous Tokens☆20Oct 12, 2025Updated 4 months ago
- Official code for "Rethinking Chain-of-Thought Reasoning for Videos"☆20Dec 14, 2025Updated 2 months ago
- official repo for `thinking with images through-self-calling`☆21Dec 28, 2025Updated 2 months ago
- Codes for the paper "BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping…☆91Jan 29, 2026Updated last month
- Official eval code for ROVER: Benchmarking Reciprocal Cross-Modal Reasoning for Omnimodal Generation☆27Dec 12, 2025Updated 2 months ago
- ☆31Feb 18, 2026Updated 2 weeks ago
- [ICCV2025] VEGGIE: Instructional Editing and Reasoning Video Concepts with Grounded Generation☆33Aug 18, 2025Updated 6 months ago
- [ACL' 25] The official code repository for PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward Models.☆88Feb 15, 2025Updated last year
- [ICLR2026] Laser: Learn to Reason Efficiently with Adaptive Length-based Reward Shaping☆63May 22, 2025Updated 9 months ago
- [ICCV 2025] UrbanLLaVA: A Multi-modal Large Language Model for Urban Intelligence with Spatial Reasoing and Understanding.☆68Feb 28, 2026Updated last week
- EchoX: Towards Mitigating Acoustic-Semantic Gap via Echo Training for Speech-to-Speech LLMs☆46Sep 19, 2025Updated 5 months ago
- Awesome paper list and repos of the paper "A comprehensive survey of embodied world models".☆75Oct 22, 2025Updated 4 months ago
- Official implementation of Rolling Sink: Bridging Limited-Horizon Training and Open-Ended Testing in Autoregressive Video Diffusion☆49Feb 23, 2026Updated 2 weeks ago