nvidia-cosmos / cosmos-reason1Links
Cosmos-Reason1 models understand the physical common sense and generate appropriate embodied decisions in natural language through long chain-of-thought reasoning processes.
☆664Updated this week
Alternatives and similar repositories for cosmos-reason1
Users that are interested in cosmos-reason1 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…☆630Updated 2 weeks ago
- Cosmos-Predict1 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world m…☆331Updated last week
- WorldVLA: Towards Autoregressive Action World Model☆363Updated last month
- Nvidia GEAR Lab's initiative to solve the robotics data problem using world models☆289Updated this week
- Official repo and evaluation implementation of VSI-Bench☆575Updated 3 weeks ago
- Implementation of π₀, the robotic foundation model architecture proposed by Physical Intelligence☆486Updated last month
- [ICLR 2025] LAPA: Latent Action Pretraining from Videos☆356Updated 7 months ago
- A flexible and efficient codebase for training visually-conditioned language models (VLMs)☆772Updated last year
- [RSS 2025] Learning to Act Anywhere with Task-centric Latent Actions☆695Updated last week
- world modeling challenge for humanoid robots☆506Updated 9 months 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
- ☆386Updated 7 months ago
- Embodied Reasoning Question Answer (ERQA) Benchmark☆207Updated 5 months ago
- Paper list in the survey: A Survey on Vision-Language-Action Models: An Action Tokenization Perspective☆214Updated last month
- OpenVLA: An open-source vision-language-action model for robotic manipulation.☆250Updated 5 months ago
- Compose multimodal datasets 🎹☆466Updated 3 weeks ago
- 🔥 SpatialVLA: a spatial-enhanced vision-language-action model that is trained on 1.1 Million real robot episodes. Accepted at RSS 2025.☆460Updated 2 months ago
- Embodied Chain of Thought: A robotic policy that reason to solve the task.☆301Updated 4 months ago
- PyTorch code and models for VJEPA2 self-supervised learning from video.☆2,124Updated this week
- Evaluating and reproducing real-world robot manipulation policies (e.g., RT-1, RT-1-X, Octo) in simulation under common setups (e.g., Goo…☆735Updated 5 months ago
- [ICML 2024] 3D-VLA: A 3D Vision-Language-Action Generative World Model☆557Updated 10 months ago
- Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success☆627Updated 4 months ago
- Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations https://video-prediction-policy.github.io☆252Updated 3 months ago
- Re-implementation of pi0 vision-language-action (VLA) model from Physical Intelligence☆1,110Updated 7 months ago
- Long-RL: Scaling RL to Long Sequences☆597Updated last week
- 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
- This repo contains the code for the paper "Intuitive physics understanding emerges fromself-supervised pretraining on natural videos"☆176Updated 6 months ago
- Heterogeneous Pre-trained Transformer (HPT) as Scalable Policy Learner.☆510Updated 8 months ago
- A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation☆320Updated 3 months ago
- Pytorch implementation of "Genie: Generative Interactive Environments", Bruce et al. (2024).☆193Updated last year