Published in NeurIPS 2025 Reliable ML from Unreliable Data Workshop (non-archival), 2024
We propose a jailbreaking technique that encodes malicious queries with layered novel ciphers, exploiting LLMs ability to interpret complex instructions, increasing jailbreaking success rates from 40% to 78%.
Published in arXiv preprint, 2024
We study the use of Retrieval-Augmented Generation to improve LLM factual accuracy and reduce hallucinations for domain-specific queries in private knowledge bases.
Published in AIP Advances, vol. 14, no. 9, 2024
We propose a new masking pretraining method for Force and Energy-Centric Graph Neural Networks to surrogate molecular dynamics, reducing RMSE for water datasets by up to 38%.
Published in Transactions on Machine Learning Research (TMLR), 2026
We construct a benchmark dataset for evaluating agentic open-source software compilation methods and propose a multi-agent compilation method enhanced with LLM-assisted retrieval.
Published in EMNLP 2026 Main Conference, 2026
We introduce critique-aware supervision for training more reliable agents on long-horizon tool-calling tasks.
Internship, Sohu Inc., 2021
Designed and deployed a real-time feed deduplication system to enhance user experience and content diversity for social media app.
Teaching Assistant, Boston College, Computer Science Department, 2021
Teaching Assistant for Randomness and Computation (CSCI2244) at Boston College.
Teaching Assistant, Boston College, Computer Science Department, 2022
Teaching Assistant for Web Application Development (CSCI2254) at Boston College.
Guest Lecturer, Arizona State University, 2024
Delivered lecture about language model-based agents.
Internship, Samsung Research America, 2026
Conducted research on indirect prompt injection vulnerabilities in LLM-based agentic systems.
Teaching Assistant, Arizona State University, 2026
Graduate Teaching Assistant for Information Assurance (CSE 365) at Arizona State University.