Yongsen Zheng
I am currently a Research Fellow in the College of Computing and Data Science at the Nanyang Technological University (NTU), Singapore, and also at the National Centre for Research in Digital Trust, Singapore (Digital Trust Centre Singapore (DTC)) as well as at the Singapore AI Safety Institute (AISI), working with Prof. Kwok-Yan Lam. Prior to that, I obtained my Ph.D. degree in the School of Computer Science and Engineering at Sun Yat-sen University, advised by IEEE Fellow Prof. Liang Lin in HCP-I2 Lab.
I also possess a wealth of experience in the corporate world. Concretely, I have ever interned at Huaweiđ„, worked at Tencentđ„, and served as a senior technical consultant at SenseTimeđ„.
Research InterestsHuman-AI Dialogue System, Conversational Recommender System, Natural Language Processing, Trustworthy AI, AI Safety, Large Language Models, and Causal Reasoning.
Latest NewsOct, 2025 đ„ I am honored to serve as an Area Chair for ACL ARR 2025.
Sep, 2025 đ„ One paper "CIREC" is accepted by TKDE 2025.
Sep, 2025 đ„ One paper is accepted by NeurIPS 2025 (Mechanistic Interpretability Workshop).
Sep, 2025 đ„ One paper is accepted by NeurIPS 2025 (Main Research Track).
Jun, 2025 đ„ One paper "ODMixer" is accepted by TKDE 2025.
May, 2025 đ„ Three papers are accepted by ACL 2025.
May, 2025 đ„ One paper "AlphaAgent" is accepted by KDD 2025.
Feb, 2025 đ„ One paper "CRA" is accepted by CVPR 2025. (Highlight)
Feb, 2025 đ„ One paper "Machine Unlearning Survey" is accepted by IEEE OJCS 2025.
Sep, 2024 đ„ One paper "HiCore" is accepted by EMNLP 2024. (Oral)
Jul, 2024 đ„ One paper "CoMoRec" is accepted by ACM MM 2024.
May, 2024 đ„ One paper "HyCoRec" is accepted by ACL 2024. (Oral)
Dec, 2023 đ„ Two papers "FacetCRS" and "Causal Approach" are accepted by AAAI 2024
Oct, 2023 đ„ One paper "HutCRS" is accepted by EMNLP 2023
Jul, 2023 đ„ One paper "Aesthetic Assessment Model" is accepted by ACM MM 2023
Jul, 2023 đ„ One paper "CIPL" is accepted by TNNLS 2023
May, 2023 đ„ One paper "KURIT-Net" is accepted by TNNLS 2023
Jul, 2021 đ„ One paper "GCFM" is accepted by TKDE 2021
Recent and Selected PapersYongsen Zheng, Guohua Wang, Jinhui Qin, Ziliang Chen, Junfan Lin, Pengxu Wei, Liang Lin, Kwok-Yan Lam. âCIREC: Causal Intervention-Inspired Policy Learning to Mitigate Exposure Bias for Interactive Recommendationâ, IEEE Transactions on Knowledge and Data Engineering (TKDE), 2025. [PDF] [CODE]
Yongsen Zheng, Zongxuan Xie, Guohua Wang, Ziyao Liu, Liang Lin, Kwok-Yan Lam. âWhy Multi-Interest Fairness Matters: Hypergraph Contrastive Multi-Interest Learning for Fair Conversational Recommender Systemâ, Association for Computational Linguistic (ACL) 2025 [PDF] [CODE]
Yongsen Zheng, Mingjie Qian, Guohua Wang, Yang Liu, Ziliang Chen, Mingzhi Mao, Liang Lin, Kwok-Yan Lam. âHyperCRS: Hypergraph-Aware Multi-Grained Preference Learning to Burst Filter Bubbles in Conversational Recommendation Systemâ, Association for Computational Linguistic (ACL) 2025 [PDF] [CODE]
Yongsen Zheng, Ruilin Xu, Guohua Wang, Liang Lin, Kwok-Yan Lam. âMitigating Matthew Effect: Multi-Hypergraph Boosted Multi-Interest Self-Supervised Learning for Conversational Recommendationâ, Proc. of Empirical Methods in Natural Language Processing (EMNLP), 2024. [PDF] [CODE]
Yongsen Zheng, Guohua Wang, Yang Liu, Liang Lin. âDiversity Matters: User-Centric Multi-Interest Learning for Conversational Movie Recommendationâ, Proc. of ACM International Conference on Multimedia (ACM MM), 2024. [PDF][CODE]
Yongsen Zheng, Ruilin Xu, Ziliang Chen, Guohua Wang, Mingjie Qian, Jinghui Qin, Liang Lin. âHyCoRec: Hypergraph-Enhanced Multi-Preference Learning for Alleviating Matthew Effect in Conversational Recommendationâ, Proc. of the Association for Computational Linguistics (ACL), 2024. [PDF] [CODE]
Yongsen Zheng, Ziliang Chen, Jinghui Qin, Liang Lin. âFacetCRS: Multi-Faceted Preference Learning for Pricking Filter Bubbles in Conversational Recommender Systemâ, Proc. of AAAI Conference on Artificial Intelligence (AAAI), 2024. [PDF] [CODE]
Yongsen Zheng, Jinghui Qin, Pengxu Wei, Ziliang Chen, Liang Lin. âCIPL: Counterfactual Interactive Policy Learning to Eliminate Popularity Bias for Online Recommendationâ, IEEE Transactions on Neural Networks and Learning Systems (TNNLS), DOI: 10.1109/TNNLS.2023.3299929, 2023. [PDF] [CODE]
Yongsen Zheng, Pengxu Wei, Ziliang Chen, Chengpei Tang, Liang Lin. âRouting User-Interest Markov Tree for Scalable Personalized Knowledge-Aware Recommendationâ, IEEE Transactions on Neural Networks and Learning Systems (TNNLS), DOI: 10.1109/TNNLS.2023.3276395, 2023. [PDF] [CODE]
Yongsen Zheng, Pengxu Wei, Ziliang Chen, Yang Cao, Liang Lin. âGraph-Convolved Factorization Machines for Personalized Recommendationâ, IEEE Transactions on Knowledge and Data Engineering (TKDE), 2021. [PDF] [CODE]
Ziyao Liu, Huanyi Ye, Chen Chen, Yongsen Zhengâ, Kwok-Yan Lam. âThreats, Attacks, and Defenses in Machine Unlearning: A Surveyâ, IEEE Open Journal of the Computer Society (IEEE OJCS), 2025. [PDF] [CODE]
Guohua Wang, Shengping Song, Wuchun He, Yongsen Zhengâ, âCMHKF: Cross-Modality Heterogeneous Knowledge Fusion for Weakly Supervised Video Anomaly Detectionâ, Proc. of Annual Meeting of the Association for Computational Linguistics (ACL), 2025. [PDF] [CODE]
Xin Jin, Wu Zhou, Jinyu Wang, Duo Xu, Yongsen Zhengâ. âAn Order-Complexity Aesthetic Assessment Model for Aesthetic-aware Music Recommendationâ, Proc. of ACM International Conference on Multimedia (ACM MM), 2023. [PDF] [CODE]
Ziliang Chen, Yongsen Zheng, Zhao-Rong Lai, Zhanfu Yang, Cuixi Li, Yang Liu, Liang Lin. âQuadratic Coreset Selection: Certifying and Reconciling Sequence and Token Mining for Efficient Instruction Tuningâ, Proc. of Neural Information Processing Systems (NeurIPS), 2025. [PDF] [CODE]
Ziliang Chen, Yongsen Zheng, Zhao-Rong Lai, Quanlong Guan, Liang Lin. âDiagnosing and Rectifying Fake OOD Invariance: A Restructured Causal Approachâ, Proc. of AAAI Conference on Artificial Intelligence (AAAI), 2024. [PDF] [CODE]
Mingjie Qian*, Yongsen Zheng*, Jinghui Qin, Liang Lin. âHutCRS: Hierarchical User-Interest Tracking for Conversational Recommender Systemâ, Proc. of Empirical Methods in Natural Language Processing (EMNLP), 2023. [PDF] [CODE]
Clement Neo, Yongsen Zheng, Kwok-Yan Lam, Luke Ong. âInterpreting Vision Grounding in Vision-Language Models: A Case Study in Coordinate Predictionâ, Mechanistic Interpretability Workshop at Neural Information Processing Systems (NeurIPS), 2025. [PDF] [CODE]
Yang Liu, Binglin Chen, Yongsen Zheng, Lechao Cheng, Guanbin Li, Liang Lin. âODMixer: Fine-grained Spatial-temporal MLP for Metro Origin-Destination Predictionâ, IEEE Transactions on Knowledge and Data Engineering (TKDE), 2025. [PDF] [CODE]
Ziyi Tang, Zechuan Chen, Jiarui Yang, Jiayao Mai, Yongsen Zheng, Keze Wang, Jinrui Chen, Liang Lin. âAlphaAgent: LLM-Driven Alpha Mining with Regularized Exploration to Counteract Alpha Decayâ, ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2025. [PDF] [CODE]
Weixing Chen, Yang Liu, Binglin Chen, Jiandong Su, Yongsen Zheng, Liang Lin. âCross-modal Causal Relation Alignment for Video Question Groundingâ, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025. [PDF] [CODE]