nvidia-cosmos / cosmos-rlLinks
Cosmos-RL is a flexible and scalable Reinforcement Learning framework specialized for Physical AI applications.
☆87Updated 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:
- ☆23Updated 2 weeks ago
- Multi-SpatialMLLM Multi-Frame Spatial Understanding with Multi-Modal Large Language Models☆142Updated 2 months ago
- [CVPR 2025 Highlight] Towards Autonomous Micromobility through Scalable Urban Simulation☆100Updated 2 weeks ago
- Long-RL: Scaling RL to Long Sequences☆568Updated last week
- A curated list of recent papers on efficient video attention for video diffusion models, including sparsification, quantization, and cach…☆32Updated 3 weeks ago
- Visual Embodied Brain: Let Multimodal Large Language Models See, Think, and Control in Spaces☆78Updated 2 months ago
- Source codes for the paper "MindJourney: Test-Time Scaling with World Models for Spatial Reasoning"☆70Updated 2 weeks ago
- [ICLR 2025] Official implementation and benchmark evaluation repository of <PhysBench: Benchmarking and Enhancing Vision-Language Models …☆67Updated 2 months ago
- Official repository for "RLVR-World: Training World Models with Reinforcement Learning", https://arxiv.org/abs/2505.13934☆74Updated 2 months ago
- Main repo for SimWorld simulator.☆59Updated last month
- A Video Tokenizer Evaluation Dataset☆129Updated 6 months ago
- Implementation of the Large Behavioral Model architecture for dexterous manipulation from Toyota Research Institute☆43Updated last week
- Memory Efficient Training Framework for Large Video Generation Model☆25Updated last year
- [ICML'25] The PyTorch implementation of paper: "AdaWorld: Learning Adaptable World Models with Latent Actions".☆133Updated last month
- Code release for "Pre-training Contextualized World Models with In-the-wild Videos for Reinforcement Learning" (NeurIPS 2023), https://ar…☆66Updated 10 months ago
- Nvidia GEAR Lab's initiative to solve the robotics data problem using world models☆247Updated last month
- mllm-npu: training multimodal large language models on Ascend NPUs☆91Updated 11 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…☆309Updated this week
- Code release for paper "Test-Time Training Done Right"☆249Updated 3 weeks ago
- ☆134Updated 7 months ago
- [CoRL 2024] VLM-Grounder: A VLM Agent for Zero-Shot 3D Visual Grounding☆111Updated 2 months ago
- Visual Planning: Let's Think Only with Images☆264Updated 2 months ago
- This repository is a collection of research papers on World Models.☆39Updated last year
- Cosmos-Predict2 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world m…☆440Updated this week
- Unified Vision-Language-Action Model☆170Updated 3 weeks ago
- Official implementation for BitVLA: 1-bit Vision-Language-Action Models for Robotics Manipulation☆69Updated 3 weeks ago
- ☆40Updated this week
- Official implementation of CEED-VLA: Consistency Vision-Language-Action Model with Early-Exit Decoding.☆29Updated last week
- Implementation of Flow Policy Optimization (FPO)☆167Updated last week
- Cosmos-Curate is a powerful video curation system that processes, analyzes, and organizes video content using advanced AI models and dist…☆52Updated this week