nvidia-cosmos / cosmos-transfer1Links
Cosmos-Transfer1 is a world-to-world transfer model designed to bridge the perceptual divide between simulated and real-world environments.
☆630Updated 3 weeks ago
Alternatives and similar repositories for cosmos-transfer1
Users that are interested in cosmos-transfer1 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…☆331Updated 2 weeks ago
- Cosmos-Predict2 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world m…☆527Updated this week
- Cosmos-Reason1 models understand the physical common sense and generate appropriate embodied decisions in natural language through long c…☆664Updated last week
- Official code for the CVPR 2025 paper "Navigation World Models".☆369Updated 2 weeks ago
- [NeurIPS 2024] A Generalizable World Model for Autonomous Driving☆785Updated 2 months ago
- [ICCV 2025] Aether: Geometric-Aware Unified World Modeling☆462Updated last month
- Open source repo for Locate 3D Model, 3D-JEPA and Locate 3D Dataset☆360Updated 2 months ago
- [ICML 2025] Official PyTorch Implementation of "History-Guided Video Diffusion"☆458Updated 2 months ago
- Nvidia GEAR Lab's initiative to solve the robotics data problem using world models☆289Updated last week
- [ICCV 2025] A Simple yet Effective Pathway to Empowering LLaVA to Understand and Interact with 3D World☆309Updated last month
- A comprehensive list of papers for the definition of World Models and using World Models for General Video Generation, Embodied AI, and A…☆366Updated this week
- [ICML 2024] 3D-VLA: A 3D Vision-Language-Action Generative World Model☆557Updated 10 months ago
- A curated list of awesome 3D scene generation papers. (arXiv 2505.05474)☆654Updated 2 weeks ago
- Towards a Generative 3D World Engine for Embodied Intelligence☆297Updated this week
- ViPE: Video Pose Engine for Geometric 3D Perception☆908Updated this week
- ☆421Updated last year
- Orient Anything, ICML 2025☆313Updated 3 months ago
- [RSS 2025] Learning to Act Anywhere with Task-centric Latent Actions☆695Updated last week
- Official implementation of Continuous 3D Perception Model with Persistent State☆1,027Updated this week
- ☆169Updated last month
- WorldVLA: Towards Autoregressive Action World Model☆363Updated last month
- [ICLR 2025] LAPA: Latent Action Pretraining from Videos☆363Updated 7 months ago
- [ICCV 2025] SpatialTrackerV2: 3D Point Tracking Made Easy☆737Updated last month
- [CVPR 2025 Highlight] GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control☆974Updated last week
- Official PyTorch Implementation of Unified Video Action Model (RSS 2025)☆259Updated last month
- [ICML'25] The PyTorch implementation of paper: "AdaWorld: Learning Adaptable World Models with Latent Actions".☆147Updated 2 months ago
- Official implementation of Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence☆328Updated 2 months ago
- Generative World Explorer☆154Updated 2 months ago
- [ICLR 2025 Spotlight] MetaUrban: An Embodied AI Simulation Platform for Urban Micromobility☆198Updated 2 weeks ago
- Paper list in the survey: A Survey on Vision-Language-Action Models: An Action Tokenization Perspective☆214Updated 2 months ago