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.
☆713Updated 2 months ago
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…☆397Updated 3 weeks ago
- Cosmos-Predict2.5, the latest version of the Cosmos World Foundation Models (WFMs) family, specialized for simulating and predicting the …☆735Updated this week
- Cosmos-Transfer2.5, built on top of Cosmos-Predict2.5, produces high-quality world simulations conditioned on multiple spatial control in…☆386Updated last week
- Cosmos-Transfer1 is a world-to-world transfer model designed to bridge the perceptual divide between simulated and real-world environment…☆766Updated 3 weeks ago
- [ICML 2025] Official PyTorch Implementation of "History-Guided Video Diffusion"☆600Updated 6 months ago
- Benchmarking physical understanding in generative video models☆233Updated 3 weeks ago
- [NeurIPS 2025] WorldMem: Long-term Consistent World Simulation with Memory☆329Updated last month
- Cosmos-Reason1 models understand the physical common sense and generate appropriate embodied decisions in natural language through long c…☆886Updated 3 weeks ago
- [ICML'25] The PyTorch implementation of paper: "AdaWorld: Learning Adaptable World Models with Latent Actions".☆192Updated 7 months ago
- Generative World Explorer☆165Updated 7 months ago
- PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation (ECCV 2024)☆331Updated last year
- PhysX: Physical-Grounded 3D Asset Generation (NeurIPS 2025, Spotlight)☆345Updated last month
- Cosmos-Curate is a powerful video curation system that processes, analyzes, and organizes video content using advanced AI models and dist…☆138Updated 2 weeks ago
- Nvidia GEAR Lab's initiative to solve the robotics data problem using world models☆453Updated 3 months ago
- ☆162Updated last year
- VITRA: Scalable Vision-Language-Action Model Pretraining for Robotic Manipulation with Real-Life Human Activity Videos☆257Updated last month
- [ICCV 2025] A Simple yet Effective Pathway to Empowering LLaVA to Understand and Interact with 3D World☆369Updated 3 months ago
- [ICCV 2025 & ICCV 2025 RIWM Outstanding Paper] Aether: Geometric-Aware Unified World Modeling☆565Updated 3 months ago
- OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling☆417Updated 3 weeks ago
- The official repository of "Astra : General Interactive World Model with Autoregressive Denoising"☆197Updated 2 weeks ago
- Official code for the CVPR 2025 paper "Navigation World Models".☆517Updated 2 months ago
- Towards a Generative 3D World Engine for Embodied Intelligence☆382Updated 2 weeks ago
- A Large-scale Video Action Dataset☆341Updated last week
- Orient Anything, ICML 2025☆373Updated 3 months ago
- The official code of Yume☆586Updated 2 weeks ago
- Official PyTorch Implementation of Unified Video Action Model (RSS 2025)☆319Updated 6 months ago
- Code for "EgoX: Egocentric Video Generation from a Single Exocentric Video"☆493Updated last week
- [ICCV 2025] GameFactory: Creating New Games with Generative Interactive Videos☆465Updated 10 months ago
- [ICLR 2025] LAPA: Latent Action Pretraining from Videos☆445Updated last year
- Open source repo for Locate 3D Model, 3D-JEPA and Locate 3D Dataset☆410Updated 7 months ago