nvidia-cosmos / cosmos-rlLinks
Cosmos-RL is a flexible and scalable Reinforcement Learning framework specialized for Physical AI applications.
☆228Updated this week
Alternatives and similar repositories for cosmos-rl
Users that are interested in cosmos-rl are comparing it to the libraries listed below
Sorting:
- Official repository for "RLVR-World: Training World Models with Reinforcement Learning" (NeurIPS 2025), https://arxiv.org/abs/2505.13934☆147Updated last month
- Official implementation for BitVLA: 1-bit Vision-Language-Action Models for Robotics Manipulation☆91Updated 4 months ago
- MiMo-Embodied☆260Updated last week
- ☆28Updated 4 months ago
- Virtual Community: An Open World for Humans, Robots, and Society☆177Updated last week
- ☆92Updated last month
- NORA: A Small Open-Sourced Generalist Vision Language Action Model for Embodied Tasks☆191Updated last week
- siiRL: Shanghai Innovation Institute RL Framework for Advanced LLMs and Multi-Agent Systems☆266Updated this week
- ☆59Updated 7 months ago
- [ICML'25] The PyTorch implementation of paper: "AdaWorld: Learning Adaptable World Models with Latent Actions".☆178Updated 5 months ago
- ☆78Updated 6 months ago
- Code release for "Pre-training Contextualized World Models with In-the-wild Videos for Reinforcement Learning" (NeurIPS 2023), https://ar…☆69Updated last year
- SimWorld: An Open-ended Realistic Simulator for Autonomous Agents in Physical and Social Worlds☆75Updated 3 weeks ago
- Implementation of the Large Behavioral Model architecture for dexterous manipulation from Toyota Research Institute☆68Updated 2 months ago
- Cosmos-Predict2.5, the latest version of the Cosmos World Foundation Models (WFMs) family, specialized for simulating and predicting the …☆439Updated this week
- Cosmos-Predict1 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world m…☆381Updated 3 months ago
- Implementation of Flow Policy Optimization (FPO)☆291Updated 2 weeks ago
- Pytorch implementation of "Genie: Generative Interactive Environments", Bruce et al. (2024).☆232Updated last year
- Embodied Reasoning Question Answer (ERQA) Benchmark☆243Updated 8 months ago
- ☆131Updated 4 months ago
- RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation☆254Updated last month
- F1: A Vision Language Action Model Bridging Understanding and Generation to Actions☆136Updated last month
- Official implementation of CEED-VLA: Consistency Vision-Language-Action Model with Early-Exit Decoding.☆44Updated 2 months ago
- Nvidia GEAR Lab's initiative to solve the robotics data problem using world models☆390Updated last month
- VLA-0: Building State-of-the-Art VLAs with Zero Modification☆312Updated last week
- [NeurIPS 2025] Source codes for the paper "MindJourney: Test-Time Scaling with World Models for Spatial Reasoning"☆98Updated 3 weeks ago
- Multi-SpatialMLLM Multi-Frame Spatial Understanding with Multi-Modal Large Language Models☆160Updated last month
- Official code of paper "DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution"☆119Updated 9 months ago
- Cosmos-Reason1 models understand the physical common sense and generate appropriate embodied decisions in natural language through long c…☆811Updated 2 weeks ago
- AutoEval: Autonomous Evaluation of Generalist Robot Manipulation Policies in the Real World | CoRL 2025☆87Updated 5 months ago