nvidia-cosmos / cosmos-reason1
Cosmos-Reason1 models understand the physical common sense and generate appropriate embodied decisions in natural language through long chain-of-thought reasoning processes.
☆218Updated this week
Alternatives and similar repositories for cosmos-reason1:
Users that are interested in cosmos-reason1 are comparing it to the libraries listed below
- 🔥 SpatialVLA: a spatial-enhanced vision-language-action model that is trained on 1.1 Million real robot episodes.☆181Updated last week
- [ICLR 2025] LAPA: Latent Action Pretraining from Videos☆199Updated 2 months ago
- A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation☆205Updated last month
- ☆312Updated 2 months ago
- Official repo and evaluation implementation of VSI-Bench☆423Updated last month
- Code for "Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation"☆239Updated 11 months ago
- Cosmos-Transfer1 is a world-to-world transfer model designed to bridge the perceptual divide between simulated and real-world environment…☆290Updated this week
- Embodied Reasoning Question Answer (ERQA) Benchmark☆106Updated 2 weeks ago
- Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success☆246Updated this week
- GRAPE: Guided-Reinforced Vision-Language-Action Preference Optimization☆98Updated last week
- OpenVLA: An open-source vision-language-action model for robotic manipulation.☆148Updated last week
- Official implementation of paper: SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training☆255Updated last month
- [CVPR 2025] The offical Implementation of "Universal Actions for Enhanced Embodied Foundation Models"☆121Updated last week
- Compose multimodal datasets 🎹☆321Updated last week
- Official repository of Learning to Act from Actionless Videos through Dense Correspondences.☆205Updated 11 months ago
- [ICML 2024] 3D-VLA: A 3D Vision-Language-Action Generative World Model☆461Updated 5 months ago
- Embodied Chain of Thought: A robotic policy that reason to solve the task.☆194Updated 3 weeks ago
- The PyTorch implementation of paper: "AdaWorld: Learning Adaptable World Models with Latent Actions".☆36Updated this week
- Official repo of VLABench, a large scale benchmark designed for fairly evaluating VLA, Embodied Agent, and VLMs.☆178Updated this week
- Pytorch implementation of "Genie: Generative Interactive Environments", Bruce et al. (2024).☆143Updated 7 months ago
- [ICML 2024] Official code repository for 3D embodied generalist agent LEO☆424Updated 2 months ago
- A Simple yet Effective Pathway to Empowering LLaVA to Understand and Interact with 3D World☆229Updated 4 months ago
- 🔥[ICLR'25] LLaRA: Supercharging Robot Learning Data for Vision-Language Policy☆200Updated this week
- Official repo of EmbodiedBench, a comprehensive benchmark designed to evaluate MLLMs as embodied agents.☆92Updated last week
- [ICLR 2025] VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation☆249Updated 2 months ago
- ☆122Updated 2 months ago
- MetaSpatial leverages reinforcement learning to enhance 3D spatial reasoning in vision-language models (VLMs), enabling more structured, …☆81Updated this week
- HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model☆130Updated this week
- Unified Video Action Model☆128Updated last week
- Official Repo for Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning☆328Updated 3 months ago