Post-training scripts and samples for NVIDIA Cosmos ecosystem
☆309Mar 16, 2026Updated this week
Alternatives and similar repositories for cosmos-cookbook
Users that are interested in cosmos-cookbook are comparing it to the libraries listed below
Sorting:
- Cosmos-Reason2 models understand the physical common sense and generate appropriate embodied decisions in natural language through long c…☆280Feb 12, 2026Updated last month
- Cosmos-Transfer2.5, built on top of Cosmos-Predict2.5, produces high-quality world simulations conditioned on multiple spatial control in…☆528Mar 10, 2026Updated last week
- Motion Planning Hyperparameter Optimization☆12Nov 2, 2022Updated 3 years ago
- Python library for building and running distributed data pipelines using Ray☆57Mar 12, 2026Updated last week
- Cosmos-Reason1 models understand the physical common sense and generate appropriate embodied decisions in natural language through long c…☆927Jan 6, 2026Updated 2 months ago
- This is a Python tool for converting USD models to MuJoCo MJCF format.☆30Jul 28, 2025Updated 7 months ago
- Cosmos-Transfer1 is a world-to-world transfer model designed to bridge the perceptual divide between simulated and real-world environment…☆785Jan 6, 2026Updated 2 months ago
- Reference workflow for generating large amounts of synthetic motion trajectories for robot manipulation from a few human demonstrations.☆196May 20, 2025Updated 10 months ago
- ☆24Feb 14, 2025Updated last year
- ☆866Mar 13, 2026Updated last week
- ☆26Mar 6, 2025Updated last year
- Official Reporsitory of "RoboEngine: Plug-and-Play Robot Data Augmentation with Semantic Robot Segmentation and Background Generation"☆151May 28, 2025Updated 9 months ago
- Driving Everywhere with Large Language Model Policy Adaptation☆17Jul 4, 2024Updated last year
- Cosmos Policy☆649Jan 23, 2026Updated last month
- keyframe-based stereo visual odometry☆10Mar 14, 2021Updated 5 years ago
- This is a python library. Install with "python3 -m pip install rp" then run with "python3 -m rp" or just "rp". Requires python≥3.5☆13Mar 9, 2026Updated last week
- DreamGen: Nvidia GEAR Lab's initiative to solve the robotics data problem using world models☆505Oct 24, 2025Updated 4 months ago
- ☆337Feb 10, 2026Updated last month
- ☆39Oct 16, 2025Updated 5 months ago
- Official Repository for the NVIDIA Fixer model☆78Nov 25, 2025Updated 3 months ago
- Implementation of ICLR 2025 paper "Q-Adapter: Customizing Pre-trained LLMs to New Preferences with Forgetting Mitigation"☆18Oct 5, 2024Updated last year
- [ICLR 26] The official code repository for the paper "Mirage or Method? How Model–Task Alignment Induces Divergent RL Conclusions".☆17Feb 9, 2026Updated last month
- Cosmos-Predict2.5, the latest version of the Cosmos World Foundation Models (WFMs) family, specialized for simulating and predicting the …☆920Mar 3, 2026Updated 2 weeks ago
- ☆1,544Mar 5, 2026Updated 2 weeks ago
- Development of a virtual simulation platform for autonomous vehicle sensing, mapping, control and behaviour methods using ROS and Gazebo.…☆35Jan 31, 2023Updated 3 years ago
- A sophisticated multi-agent system designed for real-time market analysis of HTX (formerly Huobi) exchange data. This swarm combines spec…☆10Mar 18, 2025Updated last year
- LD06 library☆16Nov 15, 2025Updated 4 months ago
- Code for Scalable Offline Model-Based RL with Action chunking☆20Feb 20, 2026Updated last month
- ☆11May 24, 2024Updated last year
- Various agents from all of the top agent frameworks to integrate into swarms! Langchain, Griptape, CrewAI, and more!☆18Dec 22, 2025Updated 2 months ago
- wrapper of curobo for ros☆32Mar 11, 2026Updated last week
- [ICLR'25] UniDrive: Towards Universal Driving Perception Across Camera Configurations☆94Jul 2, 2025Updated 8 months ago
- ☆28Feb 15, 2026Updated last month
- Tools for replaying Drake simulations in Blender☆12Feb 27, 2026Updated 3 weeks ago
- Cosmos-Predict1 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world m…☆431Jan 6, 2026Updated 2 months ago
- Code for paper "Model-free Safe Control for Zero-Violation Reinforcement Learning" at Conference on Robot Learning (CoRL) 2021.☆10Nov 1, 2021Updated 4 years ago
- [ICLR 2025] Vision-Centric Evaluation for Retrieval-Augmented Multimodal Models☆61Jan 22, 2025Updated last year
- Agentic Keyframe Search for Video Question Answering☆16Apr 7, 2025Updated 11 months ago
- [Preprint] RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments☆190Jan 12, 2026Updated 2 months ago