CV

Education

Master of Electrical and Computer Engineering (GPA: 4.0/4.0)
Sept. 2024 – Expected May 2026

Relevant Courses: Linear Algebra, Probability (PhD-level), Deep Learning, Supervised Learning, Digital Signal Processing

Bachelor of Computer Science and Technology (GPA: 3.51/4.0, Top 10%)
Sept. 2020 – Jul. 2024

Relevant Courses: Data Structures, Data Mining, Database Systems, Machine Learning, Computer Vision, NLP, Data Visualization

Research Assistant
Oct. 2024 – Present

Contributed to adaptive control for agile legged robot locomotion using reinforcement learning.
Developed a PPO-based stable walking algorithm for the bipedal robot Hector in Isaac Gym, utilizing an asymmetric actor-critic approach and a β-Variational Autoencoder (β-VAE) for reconstructing robot velocity and environmental observations to generate precise joint actions.
Implemented a control strategy for the humanoid robot G1 using imitation learning, where a well-designed reward function enables the robot to accurately replicate the dynamic motion capture data of professional dancers.

Research Assistant
Mar. 2024 – Jul. 2024

Developed an algorithm integrating reinforcement learning and column generation to solve the aircraft recovery problem, using a deep neural network to generate initial columns in a reinforcement learning environment; paper accepted at LESDCT 2024.
Utilized PPO algorithm framework, incorporating Graph Attention Networks (GAT) for flight topology graph embedding and Pointer Networks for decoding optimal initial columns.
Demonstrated generalization capability across datasets, achieving 50% faster convergence compared to baseline aircraft routing methods.

Member of the Technical Department
Oct. 2020 – Jun. 2022

Managed 3D printing and development of a diverse range of 3D models, ensuring high-quality customer service and timely delivery.
Programmed Python scripts for Maya model control and dataset collection for a 3D reconstruction project.
Contributed to a YOLO-based real-time object detection and classification project to enhance 3D data collection, as well as the development of a deep learning-based 3D reconstruction model (NeRF).

Student Research Assistant
May 2023 – Jan. 2024

Modeled the container scheduling problem in distributed edge computing microservices deployment; paper accepted by MSN 2024.
Designed a deep reinforcement learning algorithm based on SAC framework, incorporating a GRU unit in the policy network to capture decision correlations, optimizing scheduling under delay and resource constraints, achieving 65% improvement over baseline performance.
Integrated heuristic algorithms with imitation learning, freezing the actor’s GRU component to mimic heuristic behavior during pretraining, achieving 80% faster convergence after online training; work is in progress for journal submission.

Student Research Assistant
May 2023 – Jan. 2024

Developed a novel model for Aspect-Based Sentiment Analysis (ABSA), addressing limitations of traditional methods in capturing long-distance lexical relationships.
Integrated Graph Convolutional Networks (GCN), bidirectional layers, and Transformer architecture, constructing dependency trees and introducing aspect-specific masking layers and feature extraction attention mechanisms to improve sentiment analysis accuracy.
Validated the model on benchmark datasets, achieving 10% higher accuracy than baseline approaches.