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.
☆304Updated last month
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…☆567Updated last week
- Cosmos-Predict2 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world m…☆421Updated this week
- Official code for the CVPR 2025 paper "Navigation World Models".☆334Updated last week
- Cosmos-Reason1 models understand the physical common sense and generate appropriate embodied decisions in natural language through long c…☆581Updated last week
- [ICCV 2025] A Simple yet Effective Pathway to Empowering LLaVA to Understand and Interact with 3D World☆296Updated 3 weeks ago
- [ICCV 2025] Aether: Geometric-Aware Unified World Modeling☆429Updated last month
- Generative World Explorer☆150Updated last month
- [ICML 2025] Official PyTorch Implementation of "History-Guided Video Diffusion"☆426Updated last month
- ☆163Updated 5 months ago
- ☆134Updated 7 months ago
- Official implementation of Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence☆311Updated last month
- [ICML'25] The PyTorch implementation of paper: "AdaWorld: Learning Adaptable World Models with Latent Actions".☆133Updated last month
- Nvidia GEAR Lab's initiative to solve the robotics data problem using world models☆247Updated last month
- Open source repo for Locate 3D Model, 3D-JEPA and Locate 3D Dataset☆343Updated 2 months ago
- Benchmarking physical understanding in generative video models☆188Updated 2 months ago
- Orient Anything, ICML 2025☆303Updated 2 months ago
- VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction☆235Updated last week
- [ICLR 2025] LAPA: Latent Action Pretraining from Videos☆341Updated 6 months ago
- Towards a Generative 3D World Engine for Embodied Intelligence☆274Updated last week
- EgoVid-5M: A Large-Scale Video-Action Dataset for Egocentric Video Generation☆109Updated last week
- ☆166Updated 2 weeks ago
- Official PyTorch Implementation of Unified Video Action Model (RSS 2025)☆253Updated 2 weeks ago
- [ICLR 2025] Official Implementation of M3: 3D-Spatial Multimodal Memory☆168Updated 3 months ago
- WorldVLA: Towards Autoregressive Action World Model☆310Updated last month
- SceneFun3D ToolKit☆149Updated 3 months ago
- [CVPR 2024] Probing the 3D Awareness of Visual Foundation Models☆314Updated last year
- [ICLR 2025 Spotlight] MetaUrban: An Embodied AI Simulation Platform for Urban Micromobility☆199Updated last month
- [ArXiv 2025] WorldMem: Long-term Consistent World Simulation with Memory☆192Updated 2 months ago
- (CVPR 2025 Highlight) The Scene Language: Representing Scenes with Programs, Words, and Embeddings☆233Updated 3 weeks ago
- Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesis (ECCV 2024 Oral) - Official Implementation☆261Updated 9 months ago