nvidia-cosmos / cosmos-predict2Links
Cosmos-Predict2 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world models for downstream applications.
☆618Updated this week
Alternatives and similar repositories for cosmos-predict2
Users that are interested in cosmos-predict2 are comparing it to the libraries listed below
Sorting:
- Cosmos-Predict1 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world m…☆357Updated last month
- Cosmos-Transfer1 is a world-to-world transfer model designed to bridge the perceptual divide between simulated and real-world environment…☆689Updated this week
- [ICML 2025] Official PyTorch Implementation of "History-Guided Video Diffusion"☆512Updated 3 months ago
- Generative World Explorer☆157Updated 3 months ago
- Benchmarking physical understanding in generative video models☆202Updated last week
- PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation (ECCV 2024)☆311Updated 11 months ago
- [NeurIPS 2025] WorldMem: Long-term Consistent World Simulation with Memory☆238Updated last month
- Nvidia GEAR Lab's initiative to solve the robotics data problem using world models☆319Updated last month
- ☆143Updated 9 months ago
- Cosmos-Reason1 models understand the physical common sense and generate appropriate embodied decisions in natural language through long c…☆736Updated last week
- [ICCV 2025] Aether: Geometric-Aware Unified World Modeling☆490Updated 3 months ago
- Orient Anything, ICML 2025☆318Updated 4 months ago
- PhysX: Physical-Grounded 3D Asset Generation (NeurIPS 2025, Spotlight)☆273Updated 3 weeks ago
- Towards a Generative 3D World Engine for Embodied Intelligence☆309Updated last week
- [ICML'25] The PyTorch implementation of paper: "AdaWorld: Learning Adaptable World Models with Latent Actions".☆161Updated 3 months ago
- OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling☆368Updated 2 weeks ago
- Official PyTorch Implementation of Unified Video Action Model (RSS 2025)☆274Updated 2 months ago
- [ICCV 2025] A Simple yet Effective Pathway to Empowering LLaVA to Understand and Interact with 3D World☆324Updated 3 months ago
- Official code for the CVPR 2025 paper "Navigation World Models".☆406Updated last month
- A Video Tokenizer Evaluation Dataset☆134Updated 9 months ago
- [ICLR 2025] LAPA: Latent Action Pretraining from Videos☆381Updated 8 months ago
- Open source repo for Locate 3D Model, 3D-JEPA and Locate 3D Dataset☆373Updated 4 months ago
- WorldVLA: Towards Autoregressive Action World Model☆435Updated last month
- Pytorch implementation of "Genie: Generative Interactive Environments", Bruce et al. (2024).☆208Updated last year
- Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesis (ECCV 2024 Oral) - Official Implementation☆270Updated last month
- [ICCV 2025] GameFactory: Creating New Games with Generative Interactive Videos☆423Updated 6 months ago
- Code for PhysDreamer☆585Updated 8 months ago
- ☆172Updated 2 months ago
- Unified Vision-Language-Action Model☆203Updated 2 months ago
- ☆280Updated last month