nvidia-cosmos / cosmos-rlLinks
Cosmos-RL is a flexible and scalable Reinforcement Learning framework specialized for Physical AI applications.
☆204Updated 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:
- Official repository for "RLVR-World: Training World Models with Reinforcement Learning" (NeurIPS 2025), https://arxiv.org/abs/2505.13934☆130Updated last week
- Cosmos-Transfer2.5, built on top of Cosmos-Predict2.5, produces high-quality world simulations conditioned on multiple spatial control in…☆127Updated last week
- Official implementation for BitVLA: 1-bit Vision-Language-Action Models for Robotics Manipulation☆88Updated 3 months ago
- Nvidia GEAR Lab's initiative to solve the robotics data problem using world models☆358Updated 2 weeks ago
- Virtual Community: An Open World for Humans, Robots, and Society☆176Updated 2 weeks ago
- Cosmos-Predict2.5, the latest version of the Cosmos World Foundation Models (WFMs) family, specialized for simulating and predicting the …☆318Updated this week
- NORA: A Small Open-Sourced Generalist Vision Language Action Model for Embodied Tasks☆183Updated 3 months ago
- [ICML'25] The PyTorch implementation of paper: "AdaWorld: Learning Adaptable World Models with Latent Actions".☆170Updated 4 months ago
- Running VLA at 30Hz frame rate and 480Hz trajectory frequency☆118Updated last week
- Code release for paper "Test-Time Training Done Right"☆307Updated 2 months ago
- Multi-SpatialMLLM Multi-Frame Spatial Understanding with Multi-Modal Large Language Models☆159Updated last month
- Cosmos-Predict1 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world m…☆374Updated 2 months ago
- ☆28Updated 3 months ago
- ☆58Updated 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…☆655Updated last week
- Implementation of Flow Policy Optimization (FPO)☆277Updated last month
- Long-RL: Scaling RL to Long Sequences (NeurIPS 2025)☆648Updated last month
- ☆82Updated 2 weeks ago
- A Curated List of Awesome Works in World Modeling, Aiming to Serve as a One-stop Resource for Researchers, Practitioners, and Enthusiasts…☆339Updated last week
- Cosmos-Reason1 models understand the physical common sense and generate appropriate embodied decisions in natural language through long c…☆772Updated last week
- This is the code repository for IntPhys 2, a video benchmark designed to evaluate the intuitive physics understanding of deep learning mo…☆81Updated 2 weeks ago
- ☆22Updated 6 months ago
- ☆77Updated 5 months ago
- [CVPR 2025 Highlight] Towards Autonomous Micromobility through Scalable Urban Simulation☆133Updated 2 weeks ago
- WorldVLA: Towards Autoregressive Action World Model☆511Updated last month
- Cosmos-Curate is a powerful video curation system that processes, analyzes, and organizes video content using advanced AI models and dist…☆101Updated last week
- SimWorld: An Open-ended Realistic Simulator for Autonomous Agents in Physical and Social Worlds☆70Updated 3 weeks ago
- ☆210Updated 3 weeks ago
- Embodied Reasoning Question Answer (ERQA) Benchmark☆238Updated 7 months ago
- ☆149Updated 10 months ago