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.
☆680Updated last month
Alternatives and similar repositories for cosmos-predict2
Users that are interested in cosmos-predict2 are comparing it to the libraries listed below
Sorting:
- Cosmos-Predict2.5, the latest version of the Cosmos World Foundation Models (WFMs) family, specialized for simulating and predicting the …☆499Updated last week
- Cosmos-Predict1 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world m…☆387Updated 3 months ago
- Cosmos-Transfer1 is a world-to-world transfer model designed to bridge the perceptual divide between simulated and real-world environment…☆744Updated last month
- Cosmos-Transfer2.5, built on top of Cosmos-Predict2.5, produces high-quality world simulations conditioned on multiple spatial control in…☆253Updated last week
- [ICML 2025] Official PyTorch Implementation of "History-Guided Video Diffusion"☆572Updated 5 months ago
- Benchmarking physical understanding in generative video models☆222Updated last month
- PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation (ECCV 2024)☆320Updated last year
- ☆154Updated 11 months ago
- [NeurIPS 2025] WorldMem: Long-term Consistent World Simulation with Memory☆288Updated last week
- [ICML'25] The PyTorch implementation of paper: "AdaWorld: Learning Adaptable World Models with Latent Actions".☆180Updated 5 months ago
- Nvidia GEAR Lab's initiative to solve the robotics data problem using world models☆405Updated last month
- Cosmos-Curate is a powerful video curation system that processes, analyzes, and organizes video content using advanced AI models and dist…☆111Updated this week
- Generative World Explorer☆163Updated 5 months ago
- PhysX: Physical-Grounded 3D Asset Generation (NeurIPS 2025, Spotlight)☆330Updated 3 weeks ago
- Cosmos-Reason1 models understand the physical common sense and generate appropriate embodied decisions in natural language through long c…☆837Updated last month
- Orient Anything, ICML 2025☆350Updated last month
- VITRA: Scalable Vision-Language-Action Model Pretraining for Robotic Manipulation with Real-Life Human Activity Videos☆165Updated this week
- A Video Tokenizer Evaluation Dataset☆141Updated 11 months ago
- Towards a Generative 3D World Engine for Embodied Intelligence☆356Updated last week
- [ICCV 2025] GameFactory: Creating New Games with Generative Interactive Videos☆451Updated 8 months ago
- [ICCV 2025 & ICCV 2025 RIWM Outstanding Paper] Aether: Geometric-Aware Unified World Modeling☆552Updated last month
- OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling☆399Updated last week
- [ICCV 2025] A Simple yet Effective Pathway to Empowering LLaVA to Understand and Interact with 3D World☆355Updated last month
- Official PyTorch Implementation of Unified Video Action Model (RSS 2025)☆303Updated 4 months ago
- ☆343Updated 4 months ago
- Pytorch implementation of "Genie: Generative Interactive Environments", Bruce et al. (2024).☆236Updated last year
- ☆178Updated 4 months ago
- [ICLR 2025] LAPA: Latent Action Pretraining from Videos☆421Updated 10 months ago
- RynnVLA-002: A Unified Vision-Language-Action and World Model☆734Updated last week
- Implementation of Flow Policy Optimization (FPO)☆308Updated last week