thuml / MiniVeo3-ReasonerLinks
Thinking with Videos from Open-Source Priors. We reproduce chain-of-frames visual reasoning by fine-tuning open-source video models. Give it a star 🌟 if you find it useful.
☆209Updated 4 months ago
Alternatives and similar repositories for MiniVeo3-Reasoner
Users that are interested in MiniVeo3-Reasoner are comparing it to the libraries listed below
Sorting:
- [AAAI 2026] GenMAC for Compositional Text-to-Video Generation☆32Updated last month
- [ICLR 2026] Uni-CoT: Towards Unified Chain-of-Thought Reasoning Across Text and Vision☆207Updated 2 weeks ago
- [CVPR 2025] Science-T2I: Addressing Scientific Illusions in Image Synthesis☆62Updated 9 months ago
- We introduce 'Thinking with Video', a new paradigm leveraging video generation for multimodal reasoning. Our VideoThinkBench shows that S…☆237Updated last week
- Official repository of PhysMaster: Mastering Physical Representation for Video Generation via Reinforcement Learning☆57Updated 3 months ago
- [ICLR'26] Official PyTorch implementation of "Time Is a Feature: Exploiting Temporal Dynamics in Diffusion Language Models".☆59Updated last week
- Official repository for "Visual Generation Unlocks Human-Like Reasoning through Multimodal World Models", https://arxiv.org/abs/2601.1983…☆69Updated 2 weeks ago
- [NeurIPS 2025] Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations☆200Updated 4 months ago
- Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders☆202Updated last week
- Official respository for ReasonGen-R1☆74Updated 7 months ago
- ☆141Updated 3 months ago
- https://huggingface.co/datasets/multimodal-reasoning-lab/Zebra-CoT☆123Updated last week
- [NeurIPS 2025] VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models☆162Updated last month
- Official repository for the UAE paper, unified-GRPO, and unified-Bench☆158Updated 5 months ago
- Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?☆86Updated 6 months ago
- E-GRPO: High Entropy Steps Drive Effective Reinforcement Learning for Flow Models☆33Updated last month
- ☆51Updated 5 months ago
- Official Code for "ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoning"☆79Updated 2 months ago
- UniFork: Exploring Modality Alignment for Unified Multimodal Understanding and Generation☆46Updated 5 months ago
- [ICLR 2026] Official repo of paper "Reconstruction Alignment Improves Unified Multimodal Models". Unlocking the Massive Zero-shot Potenti…☆361Updated last week
- ☆52Updated last year
- [ICLR 2026] Official Implementation of Muddit [Meissonic II]: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusio…☆99Updated last week
- [ICCV 2025 Workshop Outstanding Paper Award] VChain: Chain-of-Visual-Thought for Reasoning in Video Generation☆116Updated 4 months ago
- ☆163Updated last year
- (NeurIPS 2025 D&B Track) OverLayBench: A Benchmark for Layout-to-Image Generation with Dense Overlaps☆25Updated 3 weeks ago
- Official Repo of From Masks to Worlds: A Hitchhiker’s Guide to World Models.☆73Updated 3 months ago
- Ego-R1: Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning☆139Updated 5 months ago
- [NeurIPS 2024] The official implement of research paper "FreeLong : Training-Free Long Video Generation with SpectralBlend Temporal Atten…☆64Updated 7 months ago
- MMSI-Video-Bench: A Holistic Benchmark for Video-Based Spatial Intelligence☆54Updated this week
- GoT-R1: Unleashing Reasoning Capability of MLLM for Visual Generation with Reinforcement Learning☆103Updated 2 weeks ago