Stars
Information collection for the Happy Horse AI video generator model. Official demo and updates at happyhorses.io.
InternRobotics' open platform for building generalized navigation foundation models.
HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds
A simulation-in-the-loop harness for robot AI development. Give an AI agent a goal; it generates ROS2 behavior nodes, hot-deploys in under 100ms, reads structured simulation feedback, and iterates …
Being-H is BeingBeyond's family of human-centric embodied foundation models.
Official implementation of RAE-NWM: Navigation World Model in Dense Visual Representation Space.
Collections of robotics environments geared towards benchmarking multi-task and meta reinforcement learning
cuVSLAM: CUDA-Accelerated Visual Odometry and Mapping
Causal video-action world model for generalist robot control
[ICCV 2025] Implementation for Describe Anything: Detailed Localized Image and Video Captioning
Open & Reproducible Research for Tracking VLAs
[CVPR 2025] RoboBrain: A Unified Brain Model for Robotic Manipulation from Abstract to Concrete. Official Repository.
NaviFormer: A Spatio-Temporal Context-Aware Transformer for Object Navigation (AAAI25)
Vision-and-Language Navigation in Continuous Environments using Habitat
A comprehensive list of papers for the definition of World Models and using World Models for General Video Generation, Embodied AI, and Autonomous Driving, including papers, codes, and related webs…
A Curated List of Awesome Works in World Modeling, Aiming to Serve as a One-stop Resource for Researchers, Practitioners, and Enthusiasts Interested in World Modeling.
InteriorGS: 3D Gaussian Splatting Dataset of Semantically Labeled Indoor Scenes
MWM: Mobile World Models for Action-Conditioned Consistent Prediction
[CoRL 2025] Repository relating to "TrackVLA: Embodied Visual Tracking in the Wild"
Describe Anything, Anywhere, at Any Moment (DAAAM), a novel approach to real-time, large-scale, spatio-temporal memory
[ICLR 2026] Official Code for "the Quest for Generalizable Motion Generation: Data, Model, and Evaluation"
[IROS 2024] HabiCrowd: A High Performance Simulator for Crowd-Aware Visual Navigation