Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

AI Observability & Evaluation

[RSS 2024] AdaptiGraph: Material-Adaptive Graph-Based Neural Dynamics for Robotic Manipulation

Face Interaction Graph Networks: A GNN-based rigid body physics simulator

ExoGS: A 4D Real-to-Sim-to-Real Framework for Scalable Manipulation Data Collection

RynnVLA-002: A Unified Vision-Language-Action and World Model

[RSS2025] Code for my paper "You Only Teach Once: Learn One-Shot Bimanual Robotic Manipulation from Video Demonstrations"

PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation (ECCV 2024)

[CVPR 2024 Highlight] PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamics

[CVPR'25 Oral] MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision

[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer

Grounding Image Matching in 3D with MASt3R

DUSt3R: Geometric 3D Vision Made Easy

[ICLR 2026] Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation

[ICLR 2025] From anything to mesh like human artists. Official impl. of "MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers"

✨✨【NeurIPS 2025】Official implementation of BridgeVLA

Sample code for the paper "VLM-driven Behavior Tree for Context-aware Task Planning”

Code for "Divide-Discover-Deploy" (CoRL 2025)

[ICLR 2026] Streaming 4D Visual Geometry Transformer

Independent PyTorch implementation of Scene Representation Transformer

PointWorld: Scaling 3D World Models for In-The-Wild Robotic Manipulation

BFM_Zero: A Promptable Behavioral Foundation Model for Humanoid Control Using Unsupervised Reinforcement Learning

Real-Time 6D Pose Tracker in High-Dynamic Scenes

CMU Vision-Language-Autonomy Challenge - Unity Setup

Nvdiffrast - Modular Primitives for High-Performance Differentiable Rendering

Official Implementation of "Sampling-Based System Identification with Active Exploration for Legged Robot Sim2Real Learning"

Depth Anything 3

Spatially-Enhanced Recurrent Units (SRU) - PyTorch Implementation

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.