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.
☆392Updated 4 months ago
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…☆754Updated 2 months ago
- Cosmos-Predict2 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world m…☆695Updated 2 months ago
- Cosmos-Predict2.5, the latest version of the Cosmos World Foundation Models (WFMs) family, specialized for simulating and predicting the …☆598Updated this week
- Cosmos-Transfer2.5, built on top of Cosmos-Predict2.5, produces high-quality world simulations conditioned on multiple spatial control in…☆331Updated this week
- Cosmos-Reason1 models understand the physical common sense and generate appropriate embodied decisions in natural language through long c…☆868Updated 3 weeks ago
- [ICML 2025] Official PyTorch Implementation of "History-Guided Video Diffusion"☆587Updated 6 months ago
- Official code for the CVPR 2025 paper "Navigation World Models".☆502Updated last month
- Nvidia GEAR Lab's initiative to solve the robotics data problem using world models☆428Updated 2 months ago
- [ICCV 2025 & ICCV 2025 RIWM Outstanding Paper] Aether: Geometric-Aware Unified World Modeling☆554Updated 2 months ago
- VITRA: Scalable Vision-Language-Action Model Pretraining for Robotic Manipulation with Real-Life Human Activity Videos☆239Updated 2 weeks ago
- OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling☆409Updated 3 weeks ago
- [ICML'25] The PyTorch implementation of paper: "AdaWorld: Learning Adaptable World Models with Latent Actions".☆190Updated 6 months ago
- [ICCV 2025] A Simple yet Effective Pathway to Empowering LLaVA to Understand and Interact with 3D World☆361Updated 2 months ago
- Open source repo for Locate 3D Model, 3D-JEPA and Locate 3D Dataset☆404Updated 7 months ago
- Cosmos-Curate is a powerful video curation system that processes, analyzes, and organizes video content using advanced AI models and dist…☆131Updated this week
- [ICLR 2025] LAPA: Latent Action Pretraining from Videos☆434Updated 11 months ago
- Pytorch implementation of "Genie: Generative Interactive Environments", Bruce et al. (2024).☆246Updated last year
- Official PyTorch Implementation of Unified Video Action Model (RSS 2025)☆308Updated 5 months ago
- Benchmarking physical understanding in generative video models☆225Updated this week
- Towards a Generative 3D World Engine for Embodied Intelligence☆376Updated last week
- Official implementation of Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence☆420Updated this week
- ☆355Updated last week
- [NeurIPS 2025] WorldMem: Long-term Consistent World Simulation with Memory☆302Updated 3 weeks ago
- ☆170Updated 10 months ago
- RynnVLA-002: A Unified Vision-Language-Action and World Model☆831Updated last month
- Trace Anything: Representing Any Video in 4D via Trajectory Fields☆455Updated 2 months ago
- ☆182Updated 5 months ago
- Unified Vision-Language-Action Model☆257Updated 2 months ago
- Generative World Explorer☆165Updated 6 months ago
- ☆161Updated last year