Xuetao Wei （危学涛）

Associate Professor（研究员）, Ph.D. Advisor （博士生导师）
Department of Computer Science and Engineering
Southern University of Science and Technology
E-mail: weixt x sustech y edu y cn (where x = AT and y = DOT)

Xuetao Wei has been a tenured associate professor in the department of Computer Science and Engineering at the Southern University of Science and Technology(SUSTech) since 2019 (国家重点研发计划青年科学家项目负责人、广东省青年拔尖人才). He was an assistant professor and then promoted to associate professor with tenure at the University of Cincinnati, USA. He received his Ph.D. in Computer Science (CSRankings.org) from University of California, Riverside. He has published over 120 research papers in prestigious academic conferences and journals such as CCF-A and IEEE Transactions. His research has been supported by funding agencies such as National R&D Program(国家重点研发计划), NSFC(国家自然科学基金), GD-BABRF(广东省基金), GD-DST(广东省科技厅), SZ-STI(深圳市科创局), NSF(美国国家科学基金) , DARPA(美国国防高级研究计划局) and Industry Grants(企业横向项目).

Research Interests

常年招聘：人工智能、生物医学工程、物理等相关背景的博士生、硕士生、博士后及研究助理教授，具有大模型与智能体经验者优先。

I direct the WEI Lab (We Explore Interests Lab). Currently, I focus more on developing interdisciplinary approaches to computationally solve ethics and safety problems of Artificial Intelligence (e.g., large language models, GUI agents, and embodied AI). AI must do the right thing (ethics) and do it right (safety).

One interesting concept: Agent Factors Engineering（ A因工程 ）

Topology

Teaching

Course List

Recent Publications(Full list)

Please find the source code of publications on our Lab GitHub.

  1. Can LLMs Hear the Dogwhistle? ACL Findings, 2026
  2. Fair Decision Utility in Human-AI Collaboration: Interpretable Confidence Adjustment for Humans with Cognitive Disparities. ICLR, 2026
  3. GeWu: A Culturally-Grounded Chinese Benchmark for Multi-Stage Social Bias Evaluation in Large Language Models. AAAI, 2026 Oral
  4. The Silent Amplifier: In-Context Examples Fuel Bias in Large Language Models. AAAI, 2026 Oral
  5. Mitigating Stereotypes in Text-to-Image Generation: A Novel Perspective of Selective Neural Suppression. ACM Multimedia, 2025
  6. An Experimental Study on Embodiment Forms and Interaction Modes in Affective Robots for Anxiety Relief and Emotional Connection. IJHCS, 2025
  7. LLMs Trust Humans More, That's a Problem! Unveiling and Mitigating the Authority Bias in Retrieval-Augmented Generation. ACL, 2025
  8. The Elephant in the Room: Exploring the Role of Neutral Words in Language Model Group-Agnostic Debiasing. ACL Findings, 2025
  9. Association of Objects May Engender Stereotypes: Mitigating Association-Engendered Stereotypes in Text-to-Image Generation. NeurIPS, 2024 Spotlight
  10. Unveiling the Bias Impact on Symmetric Moral Consistency of Large Language Models. NeurIPS, 2024
  11. Does Egalitarian Fairness Lead to Instability? The Fairness Bounds in Stable Federated Learning Under Altruistic Behaviors. NeurIPS, 2024
  12. Surviving in Diverse Biases: Unbiased Dataset Acquisition in Online Data Market for Fair Model Training. AIES, 2024
  13. Anti-Matthew FL: Bridging the Performance Gap in Federated Learning to Counteract the Matthew Effect. ECAI, 2024

  14. Modeling LLM Unlearning as an Asymmetric Two-Task Learning Problem. ACL, 2026
  15. MTA:A Merge-then-Adapt Framework for Personalized Large Language Models. ACL, 2026
  16. ProEchoMem: Enhancing Long Video Understanding via Multi-Trace Probe-Echo Memory. SIGIR, 2026
  17. Boosting Fine-Grained Urban Flow Inference via Lightweight Architecture and Focalized Optimization. AAAI, 2026 Oral
  18. Renormalization Group Guided Tensor Network Structure Search AAAI, 2026
  19. UniTraj: Learning a Universal Trajectory Foundation Model from Billion-Scale Worldwide Traces. NeurIPS, 2025
  20. ImPart: Importance-Aware Delta-Sparsification for Improved Model Compression and Merging in LLMs. ACL, 2025
  21. DANCE: Resource-Efficient Neural Architecture Search with Data-Aware and Continuous Adaptation. IJCAI, 2025
  22. Learning Generalized and Flexible Trajectory Models from Omni-Semantic Supervision. KDD, 2025
  23. Multi-task Offline Reinforcement Learning for Online Advertising in Recommender Systems. KDD, 2025
  24. SeqAR: Jailbreak LLMs with Sequential Auto-Generated Characters. NAACL, 2025
  25. Behavior Modeling Space Reconstruction for E-Commerce Search. TheWebConf, 2025
  26. GARLIC: GPT-Augmented Reinforcement Learning with Intelligent Control for Vehicle Dispatching. AAAI, 2025 Oral
  27. DreaMark: Rooting Watermark in Score Distillation Sampling Generated Neural Radiance Fields . AAAI, 2025
  28. Mesh Watermark Removal Attack and Mitigation: A Novel Perspective of Function Space. AAAI, 2025
  29. GLINT-RU: Gated Lightweight Intelligent Recurrent Units for Sequential Recommender Systems. ACM KDD, 2025
  30. STAR-Rec: Making Peace with Length Variance and Pattern Diversity in Sequential Recommendation. SIGIR, 2025
  31. G3: An Effective and Adaptive Framework for Worldwide Geolocalization Using Large Multi-Modality Models. NeurIPS, 2024
  32. Achieving Resolution-Agnostic DNN-based Image Watermarking: A Novel Perspective of Implicit Neural Representation. ACM Multimedia, 2024
  33. Rethinking Mesh Watermark: Towards Highly Robust and Adaptable Deep 3D Mesh Watermarking. AAAI, 2024
  34. Bi-level User Modeling for Deep Recommender Systems. IEEE ICDM, 2024
  35. ControlTraj: Controllable Trajectory Generation with Topology-Constrained Diffusion Model. ACM KDD, 2024
  36. Efficient and Robust Regularized Federated Recommendation. CIKM, 2024

Alumni （学生毕业去向）

Year 2026
Junlei Zhou (M.S. 2026, First job: Huawei Research Lab 华为实验室)
Yifan Liu (B.S. 2026, First job: MS@SUSTech 南方科技大学)
Jing Tan (B.S. 2026, First job: MS@SUSTech 南方科技大学（国优计划）)
Year 2025
Ke Mu (Ph.D. 2025, First job: Assistant Professor@Dongguan University Of Technology 东莞理工学院)
Jiashi Gao (Ph.D. 2025（期间获得比亚迪奖学金和优秀毕业生）, First job: Postdoc@Hong Kong Baptist University 香港浸会大学)
Ying Wu (Ph.D. 2025, First job: Lecturer@Fujian Agriculture and Forestry University 福建农林大学)
Yuchen Wang (M.S. 2025, First job: PhD@NJU 南京大学)
Yuchen Jiang (M.S. 2025, First job: PhD@SJTU 上海交通大学)
Zhipeng Zheng (M.S. 2025, First job: OPPO)
Peijia Qin (B.S. 2025（校十佳本科毕业生）, First job: PhD@UCSD 加州大学圣地亚哥分校)
Jiacheng Zhou (B.S. 2025, First job: PhD@SUSTech 南方科技大学)
Songjian Dai (B.S. 2025, First job: MS@SUSTech 南方科技大学)
Chenyi Liao (B.S. 2025, First job: MS@SUSTech 南方科技大学)
Year 2024
Shiyao Zhang (RAP 2024, First job: Tenure-Track Assistant Professor@Great Bay University 大湾区大学)
Guanhui Ye (M.S. 2024, First job: Tencent 腾讯)
Zuji Zhang (B.S. 2024, First job: PhD@CUHK 香港中文大学)
Jianlin Li (B.S. 2024, First job: MS@CMU 卡耐基梅隆大学)
Haozhang li (B.S. 2024, First job: MS@IIE, CAS 中国科学院信息工程研究所)
Yuxuan Li (B.S. 2024, First job: MS@SUSTech 南方科技大学)
Yi Lin (B.S. 2024, First job: MS@SUSTech 南方科技大学)
Ziyi Zhou (B.S. 2024, First job: MS@SUSTech 南方科技大学)
Lei Chen (B.S. 2024, First job: MS@SUSTech 南方科技大学)
Year 2023
Yixuan Li (B.S. 2023, First job: MS@SUSTech 南方科技大学)
Year 2022
Haotian Lu (B.S. 2022, First job: MS@UIUC 伊利诺伊大学厄巴纳-香槟分校)
Yuchen Wang (B.S. 2022, First job: MS@SUSTech 南方科技大学)
Dibo Xian (M.S. 2022, First job: Huawei 华为)
Wenhui Wang (M.S. 2022, First job: Parametrix(An interesting AI startup))
Ziwei Wang (RA 2020-2022, First job, PhD@U of Birmingham 伯明翰大学)
Xiangyu Liu (Postdoc 2022（期间获得省自然青年基金和国自然青年基金）, First job: Associate Professor@SYLU 沈阳理工大学 )
Year 2021
Guanhui Ye (B.S. 2021, First job: MS@SUSTech 南方科技大学)
Xingyu Zhu (B.S. 2021, First job: PhD@HKPolyU 香港理工大学)
Year 2020
Qinghua Zheng (B.S. 2020, First job: Tencent 腾讯)
Sen wang (B.S. 2020, First job: Tencent 腾讯)
Weiming Zhao (B.S. 2020, First job: Tencent 腾讯)
Yujie Yang (B.S. 2020, First job: Huawei 华为)
Lida Zhao (B.S. 2020, First job: MS@NTU 南洋理工大学)
Min Chen (B.S. 2020, First job: MS@SUSTech 南方科技大学)