Cosmos-RL is a flexible and scalable Reinforcement Learning framework specialized for Physical AI applications.
☆478Oct 17, 2026Updated this week
Alternatives and similar repositories for cosmos-rl
Users that are interested in cosmos-rl are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Python library for building and running distributed data pipelines using Ray☆86Sep 1, 2026Updated last month
- Cosmos-Reason1 models understand the physical common sense and generate appropriate embodied decisions in natural language through long c…☆961Jun 7, 2026Updated 4 months ago
- Cosmos-Predict2.5, the latest version of the Cosmos World Foundation Models (WFMs) family, specialized for simulating and predicting the …☆1,382Jun 8, 2026Updated 4 months ago
- Cosmos-Reason2 models understand the physical common sense and generate appropriate embodied decisions in natural language through long c…☆456Jun 7, 2026Updated 4 months ago
- Cosmos Curator is a toolkit for curating physical AI training data.☆291Updated this week
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Cosmos-Transfer2.5, built on top of Cosmos-Predict2.5, produces high-quality world simulations conditioned on multiple spatial control in…☆747Jun 30, 2026Updated 3 months ago
- Our inference and training framework to run on the Cosmos Models☆564Updated this week
- Cosmos-Predict2 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world m…☆792Oct 29, 2025Updated 11 months ago
- Cosmos-Transfer1 is a world-to-world transfer model designed to bridge the perceptual divide between simulated and real-world environment…☆828Updated 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…☆475Jun 7, 2026Updated 4 months ago
- Post-training scripts and samples for NVIDIA Cosmos ecosystem☆478Jun 7, 2026Updated 4 months ago
- Cosmos Policy☆891Jan 23, 2026Updated 8 months ago
- Cosmos-Drive-Dreams: Scalable Synthetic Driving Data Generation with World Foundation Models☆552Mar 10, 2026Updated 7 months ago
- DreamGen: Nvidia GEAR Lab's initiative to solve the robotics data problem using world models☆621Oct 24, 2025Updated 11 months ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- [RSS 2026] Causal video-action world model for generalist robot control☆1,940Jul 9, 2026Updated 3 months ago
- AlpaSim is an open-source autonomous vehicle simulation platform designed for development and testing of end-to-end AV policies☆1,271Sep 18, 2026Updated last month
- NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomou…☆12,061Updated this week
- WorldEngine: Towards the Era of Post-Training for Autonomous Driving☆520Sep 15, 2026Updated last month
- RLinf: Reinforcement Learning Infrastructure for Embodied and Agentic AI☆5,434Updated this week
- NVIDIA OmniDreams is a world model that generates photorealistic video for autonomous-driving simulation in real time.☆347Oct 2, 2026Updated 2 weeks ago
- Official Code for Epona: Autoregressive Diffusion World Model for Autonomous Driving (ICCV 2025)☆391Jul 22, 2025Updated last year
- NVIDIA Alpamayo 1.5 Nano is an open 10B reasoning VLA model for autonomous vehicles with reinforcement-learning enhanced reasoning, navig…☆368Sep 9, 2026Updated last month
- Code to pretrain, fine-tune, and evaluate DreamZero and run sim & real-world evals☆2,712Apr 19, 2026Updated 6 months ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- Isaac Lab - Arena is a robotics simulation framework that enhances NVIDIA Isaac Lab by providing a composable, scalable system for creati…☆613Updated this week
- PyTorch code and models for VJEPA2 self-supervised learning from video.☆4,788Mar 23, 2026Updated 6 months ago
- Inferix: A Block-Diffusion based Next-Generation Inference Engine for World Simulation☆140Sep 30, 2026Updated 2 weeks ago
- "World Models in a Closed-Loop World" (ICLR'26 Oral)☆211Apr 3, 2026Updated 6 months ago
- Long-RL: Scaling RL to Long Sequences (NeurIPS 2025)☆730Sep 24, 2025Updated last year
- [CoRL '25] Pseudo-Simulation for Autonomous Driving; [NeurIPS '24] NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Ben…☆1,132Oct 27, 2025Updated 11 months ago
- Code for "Evaluating Robot Policies in a World Model".☆115Nov 6, 2025Updated 11 months ago
- AlpaGym is a reinforcement-learning framework for end-to-end autonomous-driving policies.☆160Sep 3, 2026Updated last month
- Official codebase for Fast-WAM: Do World Action Models Need Test-time Future Imagination?☆1,592Aug 20, 2026Updated 2 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Simulation Platform from AgiBot☆1,427Sep 7, 2026Updated last month
- Galaxea's open-source VLA repository☆816Aug 13, 2026Updated 2 months ago
- ICLR 2026 Paper: Ctrl-World☆571Apr 8, 2026Updated 6 months ago
- HY-World 1.5: A Systematic Framework for Interactive World Modeling with Real-Time Latency and Geometric Consistency☆1,618Jun 10, 2026Updated 4 months ago
- Closed-Loop Supervised Fine-Tuning of Tokenized Traffic Models. CVPR Oral 2025.☆203Apr 4, 2025Updated last year
- [ICLR 2026] SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning☆1,888Jan 6, 2026Updated 9 months ago
- high-performance inference and serving library for interactive autoregressive video and world models☆518Updated this week