cv

Bachelor of Science

University of California, San Diego

B.S. Computer Science | Regents Scholar | GPA: 3.99/4.0

• CS: Data Structures, Algorithms, Software Engineering, Database, Operating System, Computer Security
• 3D/CG: Computer Graphics, 3D User Interaction, 3D Asset Design
• AI: Statistical Methods, Machine Learning, Deep Learning, Computer Vision I/II, ML for Music/Audio, Deep Learning for 3D Data (Graduate), ML for Robotics (Graduate)

RFCL: Reverse Forward Curriculum Learning for Extreme Sample and Demonstration Efficiency in RL

Stone Tao, Arth Shukla, Tse-kai Chan, Hao Su

International Conference on Learning Representations (ICLR) 2024

ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AI

Stone Tao, Fanbo Xiang, Arth Shukla, Yuzhe Qin, Xander Hinrichsen, Xiaodi Yuan, Chen Bao, Xinsong Lin, Yulin Liu, Tse-kai Chan, Yuan Gao, Xuanlin Li, Tongzhou Mu, Nan Xiao, Arnav Gurha, Zhiao Huang, Roberto Calandra, Rui Chen, Shan Luo, Hao Su

arXiv preprint arXiv:2410.00425, 2024

AI Research Intern

Advisor: Prof. Hao Su

Python, PyTorch, JAX, Gymnasium, Docker, Kubernetes

• Researched demo-guided deep reinforcement learning methods to effectively solve long-horizon, sparse tasks.
• Benchmarked various state-of-the-art demonstration-guided deep RL methods, including RLPD, IQL, etc., on ManiSkill2, D4RL, and Meta-World tasks. Performed experiments on Kubernetes cluster using Docker.
• Adapted TD-MPC2 to Maniskill3 CPU/GPU vectorized environments and visual (rgb) based RL.
• Researching ways to accelerate RL algorithms for better wall-time and sample efficiency in visual-based robotics environments.

Research and Development Intern

Qualcomm Institute (Calit2)

Python, PyTorch, Unreal Engine, Kubernetes, Docker, C++

• Co-developed interactive 3D avatars of historical figures in Unreal Engine 5, driven by large language models and text-to-speech/animation pipeline. Implemented a multi-speaker tracking module to drive a virtual avatar's attention and face/body motion in multiplayer VR or through webcam using Google Mediapipe.
• Developed a real-time audio-to-face pipeline that receives audio input from text-to-speech and uses NVIDIA Audio2Face through Rest API to animate facial movements on a 3D avatar. Further researched and developed a multi-context co-speech gesture generation model for virtual avatar animation.
• Developed an Unreal plugin for real-time speech gesture generation and player communication. The plugin supports seamless communication in multiplayer gameplay and between Unreal Engine and external AI models.

Software Engineer Intern

Nearal

Kotlin, Android Studio

• Developed various features for Nearal’s Android application, including a dynamic onboarding screen, a floating login interface, and an improved sign-up process, using Kotlin and Android Studio.
• Refined multiple app fragments, ensuring optimal functionality for both logged-in and logged-out users, and resolved critical issues such as photo display inconsistencies and profile identification.

Instructional Assistant

UCSD Department of Computer Science and Engineering (CSE)

• CSE 152A: Taught Computer Vision and Deep Learning concepts for a class of 150+ students and assisted 20+ students weekly with programming assignments in office hours.

Regents Scholarship

UC San Diego

The most prestigious merit scholarship awarded to undergraduate students at the University of California.

USA Computing Olympiad - Platinum Division

USACO

Highest division in the most prestigious national pre-college algorithmic programming competition.