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.
☆320Aug 23, 2026Updated 2 months 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:
- We propose Reinforcement Learning from Community Feedback (RLCF), a training paradigm that uses large-scale community signals as supervis…☆440Nov 5, 2026Updated last week
- Game-RL: Synthesizing Multimodal Verifiable Game Data to Boost VLMs' General Reasoning☆162Updated this week
- A curated list of awesome resources about reward construction for AI agents. This repository covers cutting-edge research, and practical …☆61Sep 1, 2025Updated last year
- ☆146Aug 31, 2026Updated 2 months ago
- [ICML 2026] Prism: Spectral-Aware Block-Sparse Attention☆27May 22, 2026Updated 5 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- An open-source personal academic homepage template characterized by its user-friendly design and extensive scalability.☆36Updated this week
- A persistent 3D urban-driving benchmark for evaluating LLM agents on passenger requests, driving decisions, and multi-agent traffic inter…☆12Oct 6, 2026Updated last month
- Official repository for "Visual Generation Unlocks Human-Like Reasoning through Multimodal World Models", https://arxiv.org/abs/2601.1983…☆101Mar 9, 2026Updated 8 months ago
- Thinking with Videos from Open-Source Priors. We reproduce chain-of-frames visual reasoning by fine-tuning open-source video models. Give…☆232Apr 13, 2026Updated 7 months ago
- [ICLR 2026] The official repository for paper "ThinkMorph: Emergent Properties in Multimodal Interleaved Chain-of-Thought Reasoning"☆202May 1, 2026Updated 6 months ago
- An open-weight 11B model series for long-form and real-time video understanding☆835Oct 14, 2026Updated last month
- [CVPR 2026] TiViBench: Benchmarking Think-in-Video Reasoning for Video Generative Models☆67Feb 21, 2026Updated 8 months ago
- Cambrian-S: Towards Spatial Supersensing in Video☆573Apr 3, 2026Updated 7 months ago
- This is a collection of recent papers on reasoning in video generation models.☆168Oct 12, 2026Updated last month
- 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.
- A benchmark for evaluating future-event forecasting from audio and video context in multimodal language models☆30Jan 22, 2026Updated 9 months ago
- ☆27Jan 29, 2026Updated 9 months ago
- Are Video Models Ready as Zero-shot Reasoners?☆88Nov 24, 2025Updated 11 months ago
- ☆26Mar 2, 2026Updated 8 months ago
- [ICLR2026] Laser: Learn to Reason Efficiently with Adaptive Length-based Reward Shaping☆68May 22, 2025Updated last year
- [ICML 2026] Official repo for "DiffThinker: Towards Generative Multimodal Reasoning with Diffusion Models"☆191Jan 4, 2026Updated 10 months ago
- [CVPR 2026] Official repo for "VideoSSR: Video Self-Supervised Reinforcement Learning"☆49Nov 11, 2025Updated last year
- A benchmark for testing whether coding agents can resolve engineering tasks in scientific software☆87Oct 1, 2026Updated last month
- [ICML 2025] M-STAR (Multimodal Self-Evolving TrAining for Reasoning) Project. Diving into Self-Evolving Training for Multimodal Reasoning☆76Jul 13, 2025Updated last year
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- A foundation model that generates synchronized video and audio in a single model☆1,148Updated this week
- PolicyShiftGuard: Benchmarking and Improving Policy-Adaptive Image Guardrails☆25Jul 8, 2026Updated 4 months ago
- This is a framework for evaluating reasoning in foundational Video Models.☆106May 5, 2026Updated 6 months ago
- The official code repository for the FullFront benchmark☆29May 16, 2025Updated last year
- [ACL' 25] The official code repository for PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward Models.☆95Feb 15, 2025Updated last year
- Native Multimodal Models are World Learners☆1,567Dec 30, 2025Updated 10 months ago
- https://huggingface.co/datasets/multimodal-reasoning-lab/Zebra-CoT☆140Jan 30, 2026Updated 9 months ago
- [ICML 2026] Official codebase for "Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactiv…☆1,026Oct 24, 2026Updated 3 weeks ago
- ☆19Oct 12, 2025Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- [ICLR26] Understanding VS. Generation: Navigating Optimization Dilemma in Multimodal Models☆30May 6, 2026Updated 6 months ago
- An imaginary extension of rotary position embeddings for long-context language models☆35Dec 9, 2025Updated 11 months ago
- ☆13Jul 15, 2026Updated 4 months ago
- Code repository for the ICML 2026 paper "Reasoning over Boundaries: Enhancing Specification Alignment via Test-time Deliberation".☆24Jun 14, 2026Updated 5 months ago
- ☆23Nov 21, 2025Updated 11 months ago
- [CVPR 2026] FluxMem: Adaptive Hierarchical Memory for Streaming Video Understanding☆82Mar 16, 2026Updated 8 months ago
- 启智平台任务管理 CLI:资源查询、任务提交、日志查看和 MCP/agent workflow☆152Nov 11, 2026Updated last week
Are these results useful?