韩佳乐

研究助理教授

社会科学智能中心

教育背景
  • 2018-2023：北京邮电大学计算机科学与技术 博士学位（全日制）
  • 2021-2023：新加坡科技设计大学（访问博士生）
  • 2014-2018：西安电子科技大学通信工程 本科学位（全日制）

 

工作经历：

  • 2026-至今：深圳河套学院，研究助理教授
  • 2024-2026：香港科技大学，博士后研究员
研究方向
核心研究方向：大语言模型、自然语言处理、智能体与多智能体系统、社会模拟；跨学科研究领域：AI + Business、金融文本挖掘、供应链网络分析、金融风险预测。
邮箱
jialehan@slai.edu.cn
个人简介

韩佳乐，深圳河套学院研究助理教授，加入学院前于香港科技大学商学院从事博士后研究，2023年获北京邮电大学计算机科学博士学位。研究聚焦AI+Business交叉领域，关注大语言模型、自然语言处理、智能体、社会模拟及其在经济金融场景中的应用。已在ICLR、ICML、TKDE、ACL等发表论文30余篇，多篇工作在UTD-24商科顶刊在审。欢迎计算机和经济金融等方向科研合作与学生联系。

学术著作
  1. Li X, Gao J, Lin S, Zhou X, Zhang C, Cheng B, Han J*, Wang B. Human or Machine? A Preliminary Turing Test for Speech-to-Speech Interaction. International Conference on Learning Representations, 2026. (ICLR 2026, CCF A)
  2. Chen Y, Zhang S, Han J, Meng F, Jiang H, Cheng B, Tong Q, Liu X. CGSVD: Cascaded Granular Singular Value Decomposition for Large Language Model Compression. International Conference on Machine Learning, 2026. (ICML 2026, CCF A)
  3. Zhang S, Chen Y, Han J*, Cheng B, Ma J. Beyond A Fixed Seal: Adaptive Stealing Watermark in Large Language Models. Findings of the Association for Computational Linguistics, 2026. (ACL 2026 Findings)
  4. Gu W, Wang H, Han J*, Li X, Wu Z, Xiao H, Cheng B. Analyze–Compose–Execute: A Dynamic Dialogue Framework for Multi-Agent Debate. Annual AAAI Conference on Artificial Intelligence, 2026. (AAAI 2026, CCF A)
  5. Xiao H, Li X, Pan D, Zhang L, Song Z, Han J*, Lai S, Chen W, Tang J, Wang B. Can Audio Language Models Listen Between the Lines? A Study on Metaphorical Reasoning via the UNSPOKEN. ACM International Conference on Multimedia, 2025. (ACMMM 2025 Brave New Ideas, Oral, CCF A)
  6. Chen Y, Cheng B, Han J*, Zhang Y, Li Y, Zhang S. DLP: Dynamic Layerwise Pruning in Large Language Models. International Conference on Machine Learning, 2025. (ICML 2025, CCF A)
  7. Wei Y, Han J, Yang Y. Adapting General-Purpose Embedding Models to Private Datasets Using Keyword-based Retrieval. Findings of the Association for Computational Linguistics, 2025. (ACL 2025 Findings)
  8. Wu Z, Cheng B, Han J, Ma J, Zhang S, Chen Y, Li C. VideoQA-TA: Temporal-Aware Multi-Modal Video Question Answering. Joint International Conference on Computational Linguistics, Language Resources and Evaluation, 2025. (COLING 2025, CCF B, Outstanding Paper)
  9. Han J, Cheng B, Wan Z, Lu W. Towards Hard Few-Shot Relation Classification. IEEE Transactions on Knowledge and Data Engineering, 2023. (TKDE 2023, CCF A)
  10. Han J, Zhao S, Cheng B, Ma S, Lu W. Generative Prompt Tuning for Relation Classification. Findings of the Association for Computational Linguistics: EMNLP, 2022. (Findings of EMNLP 2022)
  11. Han J, Cheng B, Lu W. Exploring Task Difficulty for Few-Shot Relation Extraction. Conference on Empirical Methods in Natural Language Processing, 2021. (EMNLP 2021, CCF B)
  12. Han J, Cheng B, Nan G. Learning Discriminative and Unbiased Representations for Few-Shot Relation Extraction. ACM International Conference on Information and Knowledge Management, 2021. (CIKM 2021, CCF B)
  13. Han J, Cheng B, Wang X. Open Domain Question Answering based on Text Enhanced Knowledge Graph with Hyperedge Infusion. Findings of the Association for Computational Linguistics: EMNLP, 2020. (Findings of EMNLP 2020)
  14. Han J, Cheng B, Wang X. Two-Phase Hypergraph based Reasoning with Dynamic Relations for Multi-Hop KBQA. International Joint Conference on Artificial Intelligence, 2020. (IJCAI 2020)

 

科研奖励：

2025：杰出论文奖，第31届国际计算语言学大会（COLING 2025）