nvidia-cosmos / cosmos-rlLinks
Cosmos-RL is a flexible and scalable Reinforcement Learning framework specialized for Physical AI applications.
☆190Updated 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☆115Updated 3 weeks ago
- ☆25Updated 2 months ago
- Official implementation for BitVLA: 1-bit Vision-Language-Action Models for Robotics Manipulation☆83Updated 3 months ago
- ☆56Updated this week
- Virtual Community: An Open World for Humans, Robots, and Society☆176Updated last week
- Nvidia GEAR Lab's initiative to solve the robotics data problem using world models☆332Updated last month
- Multi-SpatialMLLM Multi-Frame Spatial Understanding with Multi-Modal Large Language Models☆155Updated last week
- SimWorld: An Open-ended Realistic Simulator for Autonomous Agents in Physical and Social Worlds☆65Updated this week
- A Video Tokenizer Evaluation Dataset☆135Updated 9 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…☆363Updated 2 months ago
- ☆147Updated 9 months ago
- RLinf is a flexible and scalable open-source infrastructure designed for post-training foundation models (LLMs, VLMs, VLAs) via reinforce…☆512Updated last week
- [ICML'25] The PyTorch implementation of paper: "AdaWorld: Learning Adaptable World Models with Latent Actions".☆166Updated 4 months ago
- [ICLR 2025] Official implementation and benchmark evaluation repository of <PhysBench: Benchmarking and Enhancing Vision-Language Models …☆72Updated 4 months ago
- Cosmos-Reason1 models understand the physical common sense and generate appropriate embodied decisions in natural language through long c…☆747Updated 2 weeks ago
- NORA: A Small Open-Sourced Generalist Vision Language Action Model for Embodied Tasks☆178Updated 2 months ago
- Source codes for the paper "MindJourney: Test-Time Scaling with World Models for Spatial Reasoning"☆85Updated 2 months ago
- Code release for paper "Test-Time Training Done Right"☆297Updated last month
- ☆77Updated 4 months ago
- Code release for "Pre-training Contextualized World Models with In-the-wild Videos for Reinforcement Learning" (NeurIPS 2023), https://ar…☆67Updated last year
- Long-RL: Scaling RL to Long Sequences (NeurIPS 2025)☆635Updated 3 weeks ago
- Visual Embodied Brain: Let Multimodal Large Language Models See, Think, and Control in Spaces☆81Updated 4 months ago
- Cosmos-Curate is a powerful video curation system that processes, analyzes, and organizes video content using advanced AI models and dist…☆87Updated 2 weeks ago
- Cosmos-Transfer2.5, built on top of Cosmos-Predict2.5, produces high-quality world simulations conditioned on multiple spatial control in…☆88Updated this week
- Cosmos-Predict2.5, the latest version of the Cosmos World Foundation Models (WFMs) family, specialized for simulating and predicting the …☆183Updated this week
- Pytorch implementation of "Genie: Generative Interactive Environments", Bruce et al. (2024).☆208Updated last year
- Implementation of the Large Behavioral Model architecture for dexterous manipulation from Toyota Research Institute☆66Updated last month
- Cosmos-Predict2 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world m…☆633Updated last week
- ☆119Updated 3 months ago
- This is the code repository for IntPhys 2, a video benchmark designed to evaluate the intuitive physics understanding of deep learning mo…☆78Updated 3 months ago