tongjingqi / Thinking-with-VideoView external linksLinks
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.
☆237Jan 31, 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 5 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
- UnifiedToolHub is a comprehensive project supporting LLM-based tool use, designed to unify various tool-use dataset formats and provide t…☆19Jul 23, 2025Updated 6 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 6 months ago
- Thinking with Videos from Open-Source Priors. We reproduce chain-of-frames visual reasoning by fine-tuning open-source video models. Give…☆209Oct 12, 2025Updated 4 months ago
- [ICLR 2026] Official repo for "Spotlight on Token Perception for Multimodal Reinforcement Learning"☆49Jan 30, 2026Updated 2 weeks ago
- 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 4 months ago
- Official PyTorch implementation of paper “InsViE-1M: Effective Instruction-based Video Editing with Elaborate Dataset Construction”☆33Jul 28, 2025Updated 6 months ago
- [ICML 2025] M-STAR (Multimodal Self-Evolving TrAining for Reasoning) Project. Diving into Self-Evolving Training for Multimodal Reasoning☆70Jul 13, 2025Updated 7 months ago
- StableWorld: Towards Stable and Consistent Long Interactive Video Generation☆78Feb 3, 2026Updated last week
- Game-RL: Synthesizing Multimodal Verifiable Game Data to Boost VLMs' General Reasoning☆134Jan 31, 2026Updated 2 weeks ago
- [ICCV 2025 Workshop Outstanding Paper Award] VChain: Chain-of-Visual-Thought for Reasoning in Video Generation☆116Oct 7, 2025Updated 4 months ago
- 复旦研究生入学教育测试☆23Aug 28, 2025Updated 5 months ago
- ☆37Nov 26, 2025Updated 2 months ago
- Video-as-Answer: Predict and Generate Next Video Event with Joint-GRPO☆92Dec 1, 2025Updated 2 months ago
- Are Video Models Ready as Zero-shot Reasoners?☆84Nov 24, 2025Updated 2 months ago
- Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens (arXiv 2025)☆240Aug 2, 2025Updated 6 months ago
- Official code for "Rethinking Chain-of-Thought Reasoning for Videos"☆20Dec 14, 2025Updated 2 months ago
- CVPR 2025 Accepted Papers☆23Dec 20, 2025Updated last month
- ☆28Dec 18, 2025Updated last month
- [NIPS 2025] FreqPolicy: Frequency Autoregressive Visuomotor Policy with Continuous Tokens☆20Oct 12, 2025Updated 4 months ago
- VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice☆63Jan 9, 2026Updated last month
- Codes for the paper "BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping…☆91Jan 29, 2026Updated 2 weeks ago
- ☆31Dec 4, 2025Updated 2 months ago
- Rethinking the Trust Region in LLM Reinforcement Learning☆34Feb 5, 2026Updated last week
- Official eval code for ROVER: Benchmarking Reciprocal Cross-Modal Reasoning for Omnimodal Generation☆27Dec 12, 2025Updated 2 months ago
- [KernelGYM & Dr. Kernel] A distributed GPU environment and a collection of RL training methods to support RL for Kernel Generations☆83Feb 6, 2026Updated last week
- [ICCV2025] VEGGIE: Instructional Editing and Reasoning Video Concepts with Grounded Generation☆33Aug 18, 2025Updated 5 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
- EchoX: Towards Mitigating Acoustic-Semantic Gap via Echo Training for Speech-to-Speech LLMs☆47Sep 19, 2025Updated 4 months ago
- [ICLR 2026] JanusCoder: Towards a Foundational Visual-Programmatic Interface for Code Intelligence☆76Feb 9, 2026Updated last week
- ☆41Aug 26, 2025Updated 5 months ago
- OpenVE-3M: A Large-Scale High-Quality Dataset for Instruction-Guided Video Editing☆37Jan 9, 2026Updated last month
- Official repository of the paper InstructBrush: Learning Attention-based Instruction Optimization for Image Editing☆16Apr 14, 2024Updated last year
- Official repository for "Visual Generation Unlocks Human-Like Reasoning through Multimodal World Models", https://arxiv.org/abs/2601.1983…☆69Jan 28, 2026Updated 2 weeks ago
- Maximize the Resolution Potential of Pre-trained Rectified Flow Transformers☆65Oct 16, 2024Updated last year
- Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders☆205Updated this week
- ☆114Feb 3, 2026Updated last week