About

Hi. This is Zhihan GUO (郭芷含). I am a final year Ph.D. candidate at the Department of Computer Science and Engineering in The Chinese University of Hong Kong, supervised by Professor Irwin King. I received my M.S. degree from The University of Hong Kong in 2022, and my B.S. degree from the Beijing Institute of Technology in 2021.

My research generally focuses on resource-constrained domain-specific federated LLM systems, and AI4Green.

News

  • 2026 Sep: One papers has been accepted in the NeurIPS'26.
  • 2026 Aug: One papers has been accepted in the EMNLP'26.
  • 2026 July: Outstanding Student Paper Award in the WWW'26.
  • 2026 Feb: One papers has been accepted in the Interspeech'26.
  • 2026 Feb: One papers has been accepted in the WWW'26.
  • 2025 Aug: One papers has been accepted in the EMNLP'25.
  • 2024 Mar: One papers has been accepted in the WWW'24.
  • 2024 Jan: One papers has been accepted as Findings in the NAACL'24.

Publication

Conference

  • (NeurIPS'26) Remember the Decision, Not the Description: A Rate-Distortion Framework for Agent Memory[PDF][CODE][BLOG]
    Cui W., Zhu L., Li X., Guo, Z., Bai H., Hou L., and King, I.
    The Fortieth Annual Conference on Neural Information Processing Systems.
  • (EMNLP'26) A Survey of Audio Reasoning in Multimodal Foundation Models.[PDF][CODE][BLOG]
    Zou M., Guo, Z., Liang L., Wang Z., Wang Q., Wen Q, King I., Qu L, Xu Z.
    In The 2026 Conference on Empirical Methods in Natural Language Processing.
  • (WWW'26, Companion Proceedings) FedScholar: Federated Scholarly Clustering with Literature-Aligned Rewards for Academic Report Generation.[PDF][CODE][BLOG]
    Guo, Z., Zhang Y., Song Z., Xu Z., and King, I.
    In The 2026 Conference on Empirical Methods in Natural Language Processing.
  • (Interspeech'26) TurnGuide: Enhancing Meaningful Full Duplex Spoken Interactions via Dynamic Turn-Level Text-Speech Interleaving.[PDF][CODE][BLOG]
    Cui W., Zhu L., Li X., Guo, Z., Bai H., Hou L., and King, I.
    In The 2026 Interspeech.
  • (EMNLP'25) From General Reward to Targeted Reward: Improving Open-ended Long-context Generation Models.[PDF][CODE][BLOG]
    Guo, Z., Wu J., Cui W., Zhang, Y., Hu M., Wang Y., and King, I.
    In The 2025 Conference on Empirical Methods in Natural Language Processing.
  • (NAACL'24) FedLFC: Towards Efficient Federated Multilingual Modeling with LoRA-based Language Family Clustering.[PDF][CODE][BLOG]
    Guo, Z., Zhang, Y., Zhang, Z., Xu, Z., and King, I.
    In 2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics.
  • (WWW'24, Companion Proceedings) FedHLT: Efficient Federated Low-Rank Adaption with Hierarchical Language Tree for Multilingual Modeling.[PDF]
    Guo, Z., Zhang, Y., Zhang, Z., Xu, Z., and King, I.
    In Proceedings of The Web Conference 2024.

Experience

  • 2022.08 - 2027.03, Ph.D. student, Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong SAR, China.
  • 2021.08 - 2022.08, MSc student, Finance in Financial Technology, The University of Hong Kong, Hong Kong SAR, China.
  • 2017.08 - 2021.08, BSc student, Computer Science and Technology, Beijing Institute of Technology, Beijing, China.

Honors and Awards

  • Outstanding Student Paper Award, FL@FM, The Web Conference
  • PhD International Mobility for Partnerships and Collaborations Award (IMPAC), The Chinese University of Hong Kong

Professional Experience

Chair

  • ACM International Conference on Web Search and Data Mining (WSDM) 2026

Conference Reviewer

  • Association for Computational Linguistics (ACL) 2026

Journal Reviewer

  • IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
  • ACM Computing Surveys
  • IEEE Transactions on Neural Networks and Learning Systems (TNNLS)
  • IEEE Transactions on Fuzzy Systems (TFS)
  • ACM Transactions on Intelligent Systems and Technology (TIST)

Teaching

At CUHK, I work as a teaching assistant for the following undergraduate courses:
  • CSCI2100: Data Structures, Spring 2024
  • ESTR2102: Data Structures, Spring 2024