Deprecated: The each() function is deprecated. This message will be suppressed on further calls in /home/zhenxiangba/zhenxiangba.com/public_html/phproxy-improved-master/index.php on line 456 Info | Welcome to Yiliu's homepage⚛️">
Info
Name
Yang Yiliu (杨译琉), Oliver
Education
2020 - 2024
The Chinese University of Hong Kong
Bachelor of Engineering in Artificial Intelligence: Systems and Technologies
GPA: 3.82/4.00, Major GPA: 3.92/4.00, Rank: 1st/39
First Honor, ELITE Stream, Dean's List (2020 - 2024)
Graduate-level Courses: Machine Learning Theory, Foundations of Optimization, Pattern Recognition
Specialized Stream: Large-scale Artificial Intelligence - Theory and Systems
Experience
2026 Mar - Present
AI Engineer
RedotPay
Responsible for deploying AI Agents to customer service.
2025 Mar - 2026 Feb
Rule-Based Control in Multi-Agent LLM Systems
MMLab, CUHK
Developed QuadSentinel, a multi-agent control framework that translates natural language policies into machine-checkable rules for runtime enforcement.
The framework improved policy execution accuracy and provided auditable, interpretable control for multi-agent systems.
Supervised by Prof. Yue Xiangyu.
2023 May - Aug
Machine Unlearning via Continual Learning
Purdue University
Conducted research on machine unlearning using knowledge distillation and continual learning.
Developed machine unlearning methods aimed at reducing privacy risks while maintaining model performance.
Supervised by Prof. Ninghui Li.
2023 Feb - Aug
Evaluating and Improving Logical Reasoning Ability of LLMs
CSE Department, CUHK
Developed the core code of the LogicAsker framework, an automated system for evaluating and improving logical reasoning in LLMs using atomic logic rules.
Implemented fine-tuning procedures for logical reasoning tasks in large language models.
Supervised by Prof. Michael R. Lyu.
2022 Jun - Aug
Continual Learning Knowledge Graph Embeddings
CSE Department, CUHK
Developed continual learning techniques for dynamic Knowledge Graph embeddings using Elastic Weight Consolidation and edge replay sampling.
Worked on incremental update methods for knowledge graph embeddings; the project received the Best Project Award.
Supervised by Prof. James Cheng.
ICPC & OI
2020 - 2023
International Collegiate Programming Contest (ICPC)