Published:
Co-organizer of “The Full Stack of Physical AI: Simulation, Foundation Models, and Edge Deployment for Next-Generation Robotics Applications” — a half-day tutorial at CVPR 2026 in Denver, Colorado.
Published:
Custom-designed compact AI infrastructure combining 2x NVIDIA DGX Spark, 2x NVIDIA Jetson Thor, and a QNAP QSW-M7308R-4 optical switch — concentrating real AI compute power in the smallest possible footprint.
Published:
Contributing to reBot-devArm from Seeed Studio — an open-source robot arm platform designed for students, developers, and researchers.
Published:
Pioneered the build and validation of public CUDA 13.2 PyTorch wheels for the entire Jetson Orin family using the SBSA (Server Base System Architecture) path — ahead of the official JetPack 7.2 release expected in Q2 2026.
Published:
Enabled NemoClaw and OpenShell to run on Jetson AGX Orin and Orin Super Nano, bringing NVIDIA’s manipulation and functional behavior models to edge robotics platforms.
Published:
Co-author of the official Hugging Face tutorial on deploying NVIDIA Cosmos Reason 2B — a Vision-Language Model with chain-of-thought reasoning — across the entire NVIDIA Jetson family (AGX Thor, AGX Orin, Orin Super Nano) using vLLM.
Published:
edge2cloud is a collection of Machine Learning containers for NVIDIA CUDA SBSA (Server Base System Architecture) spanning Jetson, DGX Spark, and cloud deployments.
Published:
Core contributor to dusty-nv/jetson-containers — the official collection of Machine Learning containers for NVIDIA Jetson and JetPack-L4T.
Published:
decord2 is a modernized, efficient video loader for deep learning with smart shuffling — a maintained evolution of the deprecated decord library.
Published:
Implemented and optimized NeRF (Neural Radiance Fields) on NVIDIA Jetson devices at the Jetson AI Lab, enabling real-time 3D reconstruction from 2D images on edge hardware.