Democratization of RT-2 "RT-2: New model translates vision and language into action"

RAI is a vendor-agnostic agentic framework for robotics, utilizing ROS 2 tools to perform complex actions, defined scenarios, free interface execution, log summaries, voice interaction and more.

An open source framework for research in Embodied-AI from AI2.

Odyssey: Empowering Minecraft Agents with Open-World Skills

Seamlessly integrate state-of-the-art transformer models into robotics stacks

[arXiv 2023] Embodied Task Planning with Large Language Models

[CVPR'25] SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding

[CVPR 2025 Highlight🔥] Official code repository for "Inst3D-LMM: Instance-Aware 3D Scene Understanding with Multi-modal Instruction Tuning"

[IROS'25 Oral & NeurIPSw'24] Official implementation of "MineDreamer: Learning to Follow Instructions via Chain-of-Imagination for Simulated-World Control "

[NeurIPS`25] TC-Light: Temporally Coherent Generative Rendering for Realistic World Transfer

[NeurIPS 2024] GenRL: Multimodal-foundation world models enable grounding language and video prompts into embodied domains, by turning them into sequences of latent world model states. Latent state sequences can be decoded using the decoder of the model, allowing visualization of the expected behavior, before training the agent to execute it.

Official Repo of LangSuitE

Emma-X: An Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial Reasoning

[ICLR 2025 Spotlight] Official PyTorch Implementation of "What Makes a Good Diffusion Planner for Decision Making?"

[AAAI-25 Oral] Official Implementation of "FLAME: Learning to Navigate with Multimodal LLM in Urban Environments"

Python code to implement LLM4Teach, a policy distillation approach for teaching reinforcement learning agents with Large Language Model

[ICLR 2025 Spotlight] Official PyTorch Implementation of "BodyGen: Advancing Towards Efficient Embodiment Co-Design"

EmbodiedAgents is a fully-loaded ROS2 based framework for creating interactive physical agents that can understand, remember, and act upon contextual information from their environment.

OceanGym: A Benchmark Environment for Underwater Embodied Agents

[ICML 2025 Poster] Official PyTorch Implementation of "Habitizing Diffusion Planning for Efficient and Effective Decision Making"