The Hong Kong University of Science and Technology (Guangzhou)I am a Ph.D. candidate in AI Thrust at The Hong Kong University of Science and Technology (Guangzhou), advised by Prof. Hui Xiong and Prof. Ying Sun. Before that, I received my MPhil degree in Data Science from the University of Science and Technology of China (USTC) in 2023, and my B.Eng. degree in Computer Science and Technology from Hefei University of Technology (HFUT) in 2020.
My research interests include Recommender Systems, Large Language Models, and Data Mining.
Education
-
The Hong Kong University of Science and Technology (Guangzhou)Ph.D. Candidate in AI Thrust2023 - present
-
University of Science and Technology of ChinaMPhil in Data Science2020 - 2023 -
Hefei University of TechnologyB.Eng. in Computer Science and Technology2016 - 2020
Experience
-
Tencent Ads, TencentResearch Intern, Shenzhen2025.05 - 2026.02 -
Business Intelligence Lab, Baidu ResearchResearch Intern, Beijing2019.09 - 2020.09, 2021.07 - 2023.04
Honors & Awards
-
Annual Outstanding Intern Award of Baidu Research2022
-
China National Scholarship2021
-
Excellent Graduate Award of Anhui Province2020
News
Selected Publications (view all )
Collapse Hunter: Tackling the Dimensional Degeneration in Generative Ranking
Haoran Xin, Junwei Pan, Yongqi Zhou, Tianqu Zhuang, Yilong Sun, Zhixiang Feng, Shoujun Liu, Gong Chen, Shudong Huang, Haijie Gu, Hui Xiong
Conference on Neural Information Processing Systems (NeurIPS) 2026
Collapse Hunter: Tackling the Dimensional Degeneration in Generative Ranking
Haoran Xin, Junwei Pan, Yongqi Zhou, Tianqu Zhuang, Yilong Sun, Zhixiang Feng, Shoujun Liu, Gong Chen, Shudong Huang, Haijie Gu, Hui Xiong
Conference on Neural Information Processing Systems (NeurIPS) 2026
Escaping the KL Agreement Trap in On-Policy Distillation
Haoran Xin, Anhao Zhao, Ying Sun, Jin Li, Xiaoyu Shen, Hui Xiong
Conference on Empirical Methods in Natural Language Processing (EMNLP), Main Conference 2026 Oral
This paper identifies the low-KL agreement trap in on-policy distillation and proposes a training-adaptive termination rule.
Escaping the KL Agreement Trap in On-Policy Distillation
Haoran Xin, Anhao Zhao, Ying Sun, Jin Li, Xiaoyu Shen, Hui Xiong
Conference on Empirical Methods in Natural Language Processing (EMNLP), Main Conference 2026 Oral
This paper identifies the low-KL agreement trap in on-policy distillation and proposes a training-adaptive termination rule.
How Business Agglomeration Affects Individual Points-of-Interest: A Causal Effect Estimation Perspective
Haoran Xin, Xinjiang Lu, Ying Sun, Nengjun Zhu, Tong Xu, Jingbo Zhou, Hui Xiong
ACM Transactions on Knowledge Discovery from Data (TKDD) 2026
This paper applies causal inference techniques to quantify the impact of urban business agglomeration on individual POI performance.
How Business Agglomeration Affects Individual Points-of-Interest: A Causal Effect Estimation Perspective
Haoran Xin, Xinjiang Lu, Ying Sun, Nengjun Zhu, Tong Xu, Jingbo Zhou, Hui Xiong
ACM Transactions on Knowledge Discovery from Data (TKDD) 2026
This paper applies causal inference techniques to quantify the impact of urban business agglomeration on individual POI performance.
LLMCDSR: Enhancing Cross-Domain Sequential Recommendation with Large Language Models
Haoran Xin, Ying Sun, Chao Wang, Hui Xiong
ACM Transactions on Information Systems (TOIS) 2025
This paper presents LLMCDSR, a method that leverages large language models to enhance cross-domain sequential recommendation.
LLMCDSR: Enhancing Cross-Domain Sequential Recommendation with Large Language Models
Haoran Xin, Ying Sun, Chao Wang, Hui Xiong
ACM Transactions on Information Systems (TOIS) 2025
This paper presents LLMCDSR, a method that leverages large language models to enhance cross-domain sequential recommendation.
CAPTOR: A Crowd-Aware Pre-Travel Recommender System for Out-of-Town Users
Haoran Xin, Xinjiang Lu, Nengjun Zhu, Tong Xu, Dejing Dou, Hui Xiong
International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) 2022
This paper proposes CAPTOR, a crowd-aware pre-travel recommender system designed for out-of-town users.
CAPTOR: A Crowd-Aware Pre-Travel Recommender System for Out-of-Town Users
Haoran Xin, Xinjiang Lu, Nengjun Zhu, Tong Xu, Dejing Dou, Hui Xiong
International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) 2022
This paper proposes CAPTOR, a crowd-aware pre-travel recommender system designed for out-of-town users.
Out-of-Town Recommendation with Travel Intention Modeling
Haoran Xin, Xinjiang Lu, Tong Xu, Hao Liu, Jingjing Gu, Dejing Dou, Hui Xiong
AAAI Conference on Artificial Intelligence (AAAI) 2021
This paper addresses the challenge of recommending points-of-interest to out-of-town users by modeling travel intentions.
Out-of-Town Recommendation with Travel Intention Modeling
Haoran Xin, Xinjiang Lu, Tong Xu, Hao Liu, Jingjing Gu, Dejing Dou, Hui Xiong
AAAI Conference on Artificial Intelligence (AAAI) 2021
This paper addresses the challenge of recommending points-of-interest to out-of-town users by modeling travel intentions.