Guofu Xie

He is currently a first-year Ph.D. student at Gaoling School of Artificial Intelligence, Renmin University of China. He is working in IIR lab. His supervisor is AP. Xiao Zhang and Prof. Jun Xu. His major research interests are about Large Language Models, Reinforcement Learning (especially Multi-Objective RL), Controllable Generation, Model Merging etc.

Education

09.2024-present Ph.D. Candidate, Gaoling School of Artificial Intelligence, Renmin University of China.
09.2020-06.2024 B.E., School of Computer Science, Beijing University of Posts and Telecommunications.

(First author) “Bone Soups: A Seek-and-Soup Model Merging Approach for Controllable Multi-Objective Generation.” ACL’25 Long Main
(Fifth author) “A Survey of Controllable Learning: Methods and Applications in Information Retrieval.” Frontiers of Computer Science (2025).
(Co-First author) “LexPam: Legal Procedure Awareness-Guided Mathematical Reasoning.” Submitted to EMNLP2025.
(First author) “FedSKU: Defending Backdoors in Federated Learning Through Selective Knowledge Unlearning” Arxiv’24.

Silver Medal, The 46th ICPC Asia Regional Contest (Shanghai), Nov 2021
First Prize, The 13th The Chinese Mathematics Competitions , Oct 2021
First-Class Scholarship in Beijing University of Posts and Telecommunications, 2020-2021
Second-Class Scholarship in Beijing University of Posts and Telecommunications, 2021-2022
Merit Student Scholarship in Beijing University of Posts and Telecommunications, 2020-2021 & 2021-2022