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.
☆670Updated 3 weeks 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…☆378Updated 3 months ago
- Cosmos-Transfer1 is a world-to-world transfer model designed to bridge the perceptual divide between simulated and real-world environment…☆729Updated 3 weeks ago
- Cosmos-Predict2.5, the latest version of the Cosmos World Foundation Models (WFMs) family, specialized for simulating and predicting the …☆410Updated last week
- Cosmos-Transfer2.5, built on top of Cosmos-Predict2.5, produces high-quality world simulations conditioned on multiple spatial control in…☆205Updated last week
- [ICML 2025] Official PyTorch Implementation of "History-Guided Video Diffusion"☆554Updated 4 months ago
- A Curated List of Awesome Works in World Modeling, Aiming to Serve as a One-stop Resource for Researchers, Practitioners, and Enthusiasts…☆782Updated last week
- Benchmarking physical understanding in generative video models☆219Updated 3 weeks ago
- [NeurIPS 2025] WorldMem: Long-term Consistent World Simulation with Memory☆268Updated 3 weeks ago
- Generative World Explorer☆159Updated 5 months ago
- [ICML'25] The PyTorch implementation of paper: "AdaWorld: Learning Adaptable World Models with Latent Actions".☆175Updated 5 months ago
- ☆150Updated 10 months ago
- PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation (ECCV 2024)☆317Updated last year
- Cosmos-Reason1 models understand the physical common sense and generate appropriate embodied decisions in natural language through long c…☆799Updated last week
- Nvidia GEAR Lab's initiative to solve the robotics data problem using world models☆380Updated 3 weeks ago
- PhysX: Physical-Grounded 3D Asset Generation (NeurIPS 2025, Spotlight)☆309Updated this week
- Orient Anything, ICML 2025☆348Updated last month
- Pytorch implementation of "Genie: Generative Interactive Environments", Bruce et al. (2024).☆226Updated last year
- Towards a Generative 3D World Engine for Embodied Intelligence☆341Updated last week
- Official PyTorch Implementation of Unified Video Action Model (RSS 2025)☆291Updated 3 months ago
- [ICCV 2025 & ICCV 2025 RIWM Outstanding Paper] Aether: Geometric-Aware Unified World Modeling☆534Updated 3 weeks ago
- ☆326Updated 3 months ago
- [ICCV 2025] A Simple yet Effective Pathway to Empowering LLaVA to Understand and Interact with 3D World☆348Updated last month
- Official code for the CVPR 2025 paper "Navigation World Models".☆440Updated 3 months ago
- Native Multimodal Models are World Learners☆1,265Updated this week
- Open source repo for Locate 3D Model, 3D-JEPA and Locate 3D Dataset☆387Updated 5 months ago
- [ICCV 2025] GameFactory: Creating New Games with Generative Interactive Videos☆440Updated 8 months ago
- ☆177Updated 3 months ago
- OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling☆389Updated last week
- A Video Tokenizer Evaluation Dataset☆138Updated 10 months ago
- VITRA: Scalable Vision-Language-Action Model Pretraining for Robotic Manipulation with Real-Life Human Activity Videos☆102Updated 3 weeks ago