PhD Student · Computer Science · Purdue University
I am a Ph.D. student in the Department of Computer Science at Purdue University, co-advised by Prof. Lin Tan and Prof. Aniket Bera. I received my B.E. in Computer Science from the Southern University of Science and Technology, where I worked with Prof. Shin Hwei Tan.
Vision-Language-Action Policies, Action Correction, and Safe Robot Task Planning.
LLM Planners, Coding Agents, and Preference Optimization.
A separate corrective policy that revises the action chunks proposed by a frozen flow-based VLA before execution, trained with supervised flow matching followed by correction preference optimization. Consistent gains on SimplerEnv, CALVIN, and real-robot tasks across π0.5, FLOWER VLA, and Xiaomi-Robotics-0.
A study of 1,200 Claude Code and Mini-SWE-Agent trajectories on SWE-bench that identifies three recurring cost-inefficient behaviors, then shows developer-designed skills cut task cost by up to 41.73%, roughly twice the gain of agent-synthesized skills.
Equivalence voting over LTL formulas, LTL-constrained decoding, and domain-specific fine-tuning make LLM planners follow complex user constraints, improving safety rate by 10.8% and plan efficiency by 19.8% on drone navigation.
How Effective Are Neural Networks for Fixing Security Vulnerabilities. Yi Wu, Nan Jiang, Hung Viet Pham, Thibaud Lutellier, Jordan Davis, Lin Tan, Petr Babkin, Sameena Shah.
Anti-patterns for Java Automated Program Repair Tools. Yi Wu. Won 1st Place.
Advisors: Prof. Lin Tan and Prof. Aniket Bera
Advisor: Prof. Shin Hwei Tan
Purdue CS News: SELP named a Best Paper Award Finalist at ICRA 2025.
SUSTech CS News: First place in the ACM Student Research Competition at ASE 2020.