-
Nvidia
- Shanghai
-
18:46
(UTC +08:00) - https://dorniwang.github.io/
Stars
USDCraft: Geometrically Grounded Programmatic Modeling of Articulated 3D Assets for Simulation
Official Code for "Coser: Coordinating LLM-Based Persona Simulation of Established Roles"
Official Repository of Agentic World Action Models
Fewer Tokens, Better Action: GPT-6 Astra Robot Agents with 14% Higher Success but 65% Fewer Tokens
An open agentic toolkit for physics-based Real2Sim of Robot Manipulation Tasks
Reverse engineer anything with agents, from app behavior down to native binaries.
Experimental MaleCNS-derived vision and proprioception control for a robot-arm simulator.
Experimental Drosophila-inspired camera-to-robot bridge. Working mock neural backend, optical flow, IMU feedback and UDP motor control. MaleCNS integration planned.
Fly-connectome simulation controlling a live Doom arena, with experimental neural plasticity, spectator UI, and scientific validation reports.
Open data and scalable training for long-horizon video world models.
SoL-Pi: Scaling Auto-Research Loops for Efficient Agent Harnesses
VideoDeltaNet-H3: Live T2VA / I2VA / FL2VA / Ref2VA-like generation based on Minimax H3.
PACE: A systematic approach for sim-to-real transfer of legged robots, identifying actuator and joint dynamics with standard joint encoders.
A practical toolkit for process-level robot evaluation with Process Reward Models (PRMs).
Benchmarking Knowledge Transfer in Lifelong Robot Learning
Evaluation toolkit for action-conditioned world models
Shared capture infrastructure for teleoperation and egocentric data.
Official implementation of AstraBrain-WBC 0.5
[CVPR 2026] Towards Real-Time Diffusion-Based Streaming Video Super-Resolution — An efficient one-step diffusion framework for streaming VSR with locality-constrained sparse attention and a tiny co…
Infinite Worlds with Versatile Interactions
An Open-World Foundation Model for General-Purpose Embodied Intelligence.
An Open-Source World Model for Action-Conditioned Embodied Intelligence.
FlashRT is a high-performance realtime inference engine for small-batch, latency-sensitive AI workloads. The flagship integration is production VLA control for Pi0, Pi0.5, GROOT N1.6, and Pi0-FAST.…
[NIPS 2026 Reviewed (6/5/4)] PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulation
Agent Skills for NVIDIA products — install into Claude Code, Codex, and other coding agents to run Physical AI, robotics, simulation, CUDA, and RAG workflows end to end.