nvidia-cosmos / cosmos-rlLinks
Cosmos-RL is a flexible and scalable Reinforcement Learning framework specialized for Physical AI applications.
☆238Updated last week
Alternatives and similar repositories for cosmos-rl
Users that are interested in cosmos-rl are comparing it to the libraries listed below
Sorting:
- Real-Time VLAs via Future-state-aware Asynchronous Inference.☆229Updated last week
- Official repository for "RLVR-World: Training World Models with Reinforcement Learning" (NeurIPS 2025), https://arxiv.org/abs/2505.13934☆158Updated last month
- siiRL: Shanghai Innovation Institute RL Framework for Advanced LLMs and Multi-Agent Systems☆309Updated this week
- MiMo-Embodied☆304Updated last month
- Official implementation for BitVLA: 1-bit Vision-Language-Action Models for Robotics Manipulation☆96Updated 5 months ago
- Cosmos-Predict2.5, the latest version of the Cosmos World Foundation Models (WFMs) family, specialized for simulating and predicting the …☆519Updated this week
- [ICML'25] The PyTorch implementation of paper: "AdaWorld: Learning Adaptable World Models with Latent Actions".☆183Updated 6 months ago
- Nvidia GEAR Lab's initiative to solve the robotics data problem using world models☆419Updated last month
- Running VLA at 30Hz frame rate and 480Hz trajectory frequency☆319Updated last week
- NORA: A Small Open-Sourced Generalist Vision Language Action Model for Embodied Tasks☆195Updated last month
- ☆29Updated 4 months ago
- ☆59Updated 8 months ago
- Cosmos-Predict1 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world m…☆388Updated 4 months ago
- ☆97Updated last month
- Cosmos-Transfer2.5, built on top of Cosmos-Predict2.5, produces high-quality world simulations conditioned on multiple spatial control in…☆269Updated last week
- Cosmos-Reason1 models understand the physical common sense and generate appropriate embodied decisions in natural language through long c…☆852Updated last month
- RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation☆270Updated 2 weeks ago
- Embodied Reasoning Question Answer (ERQA) Benchmark☆249Updated 9 months ago
- Pytorch implementation of "Genie: Generative Interactive Environments", Bruce et al. (2024).☆238Updated last year
- Virtual Community: An Open World for Humans, Robots, and Society☆177Updated 3 weeks ago
- Visual Embodied Brain: Let Multimodal Large Language Models See, Think, and Control in Spaces☆87Updated 6 months ago
- ☆339Updated this week
- ☆23Updated 7 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…☆683Updated last month
- Implementation of Flow Policy Optimization (FPO)☆314Updated 2 weeks ago
- VLA-0: Building State-of-the-Art VLAs with Zero Modification☆346Updated last week
- Code release for "Pre-training Contextualized World Models with In-the-wild Videos for Reinforcement Learning" (NeurIPS 2023), https://ar…☆69Updated last year
- ☆57Updated 2 weeks ago
- ☆137Updated 5 months ago
- A Video Tokenizer Evaluation Dataset☆141Updated 11 months ago