Highlights
- Pro
Stars
[ICRA 2025 & IJRR 2026] Gaussian-LIC2: LiDAR-Inertial-Camera Gaussian Splatting SLAM (in Real Time)
LAP: Language-Action Pre-Training Enables Zero-Shot Cross Embodiment Transfer
[CORL2026] Official implementation of the paper: "OptiGeo: Efficient Monocular Geometry for Embodied Perception in Optically Challenging Scenes"
[NeurIPS 2026] The Official Implementation of "ODEWorld: A Continuous Predictive Architecture via Physical-Time Flow"
[ICLR 2026] Disentangled Robot Learning via Separate Forward and Inverse Dynamics Pretraining
InfiniSplat Series: Feed-Forward 3D Gaussian Reconstruction
[ECCV 2026 Best Paper Award Candidate] LingBot-Map: Geometric Context Transformer for Streaming 3D Reconstruction
[NeurIPS 2026 Oral] Source codes for the paper "SyncWorld: Visual Calibration Enables World Models as Zero-Shot Simulators"
[NeurIPS 2026 Oral] Official implementation for "Language-Conditioned World Modeling for Visual Navigation"
Being-H is BeingBeyond's family of human-centric embodied foundation models.
Code to pretrain, fine-tune, and evaluate DreamZero and run sim & real-world evals
ODE Policy: Robot Learning via Action Dynamics, Not Actions (arXiv:2611.01729)
[CVPR 2026] SpatialVID: A Large-Scale Video Dataset with Spatial Annotations
[CoRL 2026 Spotlight] SidewalkBench: Benchmarking Visual Navigation on Urban Sidewalks
world-gymnast / world-gymnast
Forked from PRIME-RL/SimpleVLA-RLWorld-Gymnast: Training Robots with Reinforcement Learning in a World Model
ScaleNav: Scalable Internet Video Pretraining for Language-Conditioned Local Navigation
[RSS'26] Welcome to Psi-Zero, a Humanoid VLA towards Universal Humanoid Intelligence.
NORA-1.5: A Vision-Language-Action Model Trained using World Model- and Action-based Preference Rewards
[CoRL 2026] LEGS: Fine-Tuning Teleop-Free VLAs for Humanoid Loco-manipulation in an Embodied Gaussian Splatting World
Monocular whole-body 3D human pose estimation using the SOMA body model
DriveTTO: Understanding Search and Selection in Test-Time Trajectory Optimization
Official GitHub repository for the NeurIPS 2026 paper HaM-World: Soft-Hamiltonian World Models with Selective Memory for Planning.
[CVPR 2024] Official implementation of the paper "Visual In-context Learning"
ViRDM: Taming Representation Distribution Matching for Few-Step Causal Video Generation
OpenBot leverages smartphones as brains for low-cost robots. We have designed a small electric vehicle that costs about $50 and serves as a robot body. Our software stack for Android smartphones su…
moojink / openvla-oft
Forked from openvla/openvlaFine-Tuning Vision-Language-Action Models: Optimizing Speed and Success