nvidia-cosmos / cosmos-predict1Links
Cosmos-Predict1 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world models for downstream applications.
☆245Updated this week
Alternatives and similar repositories for cosmos-predict1
Users that are interested in cosmos-predict1 are comparing it to the libraries listed below
Sorting:
- Cosmos-Transfer1 is a world-to-world transfer model designed to bridge the perceptual divide between simulated and real-world environment…☆482Updated this week
- Cosmos-Reason1 models understand the physical common sense and generate appropriate embodied decisions in natural language through long c…☆458Updated this week
- [ICML 2025] Official PyTorch Implementation of "History-Guided Video Diffusion"☆342Updated last week
- Official code for the CVPR 2025 paper "Navigation World Models".☆185Updated last month
- [ICLR 2025] Official Implementation of M3: 3D-Spatial Multimodal Memory☆162Updated last month
- Aether: Geometric-Aware Unified World Modeling☆326Updated this week
- VaViM and VaVAM: Autonomous Driving through Video Generative Modeling (official repository).☆92Updated this week
- ☆162Updated 3 months ago
- ☆145Updated 3 weeks ago
- [ICML'25] The PyTorch implementation of paper: "AdaWorld: Learning Adaptable World Models with Latent Actions".☆85Updated last week
- Benchmarking physical understanding in generative video models☆168Updated 2 weeks ago
- [ICLR 2025] LAPA: Latent Action Pretraining from Videos☆293Updated 4 months ago
- A Simple yet Effective Pathway to Empowering LLaVA to Understand and Interact with 3D World☆262Updated 6 months ago
- Codebase for the WayveScenes101 Dataset☆179Updated 8 months ago
- Open source repo for Locate 3D Model, 3D-JEPA and Locate 3D Dataset☆285Updated this week
- EgoVid-5M: A Large-Scale Video-Action Dataset for Egocentric Video Generation☆104Updated 6 months ago
- A framework for 4D reconstruction from monocular videos.☆312Updated 4 months ago
- [ICLR 2025 Spotlight] MetaUrban: An Embodied AI Simulation Platform for Urban Micromobility☆177Updated 3 weeks ago
- Official PyTorch Implementation of Unified Video Action Model (RSS 2025)☆203Updated 2 months ago
- Generative World Explorer☆143Updated 6 months ago
- [CVPR 2024] Probing the 3D Awareness of Visual Foundation Models☆311Updated 10 months ago
- ☆129Updated 5 months ago
- PhysTwin: Physics-Informed Reconstruction and Simulation of Deformable Objects from Videos☆223Updated 2 weeks ago
- SceneFun3D ToolKit☆136Updated last month
- (CVPR 2025 Highlight) The Scene Language: Representing Scenes with Programs, Words, and Embeddings☆205Updated 3 months ago
- ☆140Updated last month
- Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesis (ECCV 2024 Oral) - Official Implementation☆253Updated 7 months ago
- Orient Anything, ICML 2025☆276Updated 3 weeks ago
- [ICRA, 2025] SplatSim: Zero-Shot Sim2Real Transfer of RGB Manipulation Policies Using Gaussian Splatting☆106Updated 3 weeks ago
- A Video Tokenizer Evaluation Dataset☆120Updated 4 months ago