Large-Scale Visual Representation Model
RAI is a vendor agnostic agentic framework for Physical AI robotics, utilizing ROS 2 tools to perform complex actions, defined scenarios, free interface execution, log summaries, voice interaction and more.
openeta: embodied task agent
Emma-X: An Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial Reasoning
[EMNLP 2026] Aligning Agentic World Models via Knowledgeable Experience Learning
An advanced embodied AI agent with personality-driven interactions, multi-modal perception (vision, speech), autonomous task execution, and real-time voice synthesis. Inspired by robotics subsumption architectures, it bridges cognitive reasoning, behavioral decision-making, and virtual/physical body control for immersive AI experiences.
VRM-native motion model project for interactive embodied avatars, aiming to generate continuous skeletal motion from text and dialogue context. Includes motion data preparation, VRM-centered representation, training pipelines, preview/evaluation tools, and runtime playback.
A universal system framework for grasping objects and placing them at designated locations in the real world
Official implementation for "Consistent Attack: Universal Adversarial Perturbation on Embodied Vision Navigation" (PRL 2023)
📹 Enhance computer vision with temporal reasoning for deeper understanding of video sequences, causal analysis, and event prediction.
Build a minimal Python executive AI agent with fully commented code for learning, teaching, and junior developers
Add a description, image, and links to the embodied-artificial-intelligence topic page so that developers can more easily learn about it.
To associate your repository with the embodied-artificial-intelligence topic, visit your repo's landing page and select "manage topics."