I am a PhD student in NUS IDS&SoC work with Bryan Hooi, See Kiong Ng and Luu Anh Tuan(NTU). Previously I visisted UCL WI group and AI centre. Before that I worked as a R&D engineer in natural language processing working with Prof. Zhang Richong (张日崇), affiliated with BDBC and Computer Science College in Beihang University. My current research interests lie in LLM applications on task-oriented dialogue system, reasoning and calibration capability of LLM, as well as the LLM-powered Agent.

🔥 News

• 2024.09: 🎉 One papers is accepted by NeurIPS 2024 and nominated as paper reward by reviewer.
• 2024.09: 🎉 Two papers are accepted by EMNLP 2024.
• 2024.03: 🎉 Two papers are accepted by ICLR 2024 LLM Agent Workshop and UoT paper is nominated as the best paper candidate.
• 2024.01: 🎉 One paper is accepted by ICLR 2024.
• 2023.12: 🎉 Two papers are accepted by AAAI 2024.

📝 Publications

Preprint

LongRecipe: Recipe for Efficient Long Context Generalization in Large Language Models

Zhiyuan Hu, Yuliang Liu, Jinman Zhao, Suyuchen Wang, Yan Wang, Wei Shen, Qing Gu, Anh Tuan Luu, See-Kiong Ng, Zhiwei Jiang, Bryan Hooi

Preprint

CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databases

Xiangyan Liu, Bo Lan, Zhiyuan Hu, Yang Liu, Zhicheng Zhang, Wenmeng Zhou, Fei Wang, Michael Shieh

NeurIPS 2024 & ICLR 2024@LLM Agent Workshop

Uncertainty of Thoughts: Uncertainty-Aware Planning Enhances Information Seeking in Large Language Models

Zhiyuan Hu, Chumin Liu, Xidong Feng, Yilun Zhao, See-Kiong Ng, Anh Tuan Luu, Junxian He, Pang Wei Koh, Bryan Hooi.

ICLR 2024

Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs

Miao Xiong, Zhiyuan Hu, Xinyang Lu, Yifei Li, Jie Fu, Junxian He, Bryan Hooi

EMNLP 2024 & ICLR 2024@LLM Agent Workshop

MAgIC: Investigation of Large Language Model Powered Multi-Agent in Cognition, Audaptabiulity, Ratiuonality and Cuollaboration.

Lin Xu, Zhiyuan Hu, Daquan Zhou, Hongyu Ren, Zhen Dong, Kurt Keutze, See-Kiong Ng, Jiashi Feng. (Co-first Author)

CIKM 2023

Unlocking the Potential of User Feedback: Leveraging Large Language Model as User Simulator to Enhance Dialogue System

Zhiyuan Hu, Yue Feng, Anh Tuan Luu, Bryan Hooi, Aldo Lipani.

EMNLP 2018

Syntax Encoding with Application in Authorship Attribution

Zhiyuan Hu, Richong Zhang, Hongyu Guo, and Yongyi Mao

• AAAI 2024 PoetryDiffusion: Towards Joint Semantic and Metrical Manipulation in Poetry Generation., Zhiyuan Hu, Chumin Liu, Yue Feng, Bryan Hooi.

• AAAI 2024 READ-PVLA: Recurrent Adapter with Partial Video-Language Alignment for Parameter-Efficient Transfer Learning in LowResource Video-Language Modeling., Thong Nguyen, Xiaobao Wu, Xinshuai Dong, Khoi Le, Zhiyuan Hu, Cong-Duy Nguyen, See Kiong Ng, Anh Tuan Luu.

• EMNLP 2024 Encoding and Controlling Global Semantics for Long-form Video Question Answering., Thong Thanh Nguyen, Zhiyuan Hu, Xiaobao Wu, Cong-Duy T Nguyen, See-Kiong Ng, Anh Tuan Luu.

• Preprint Enhancing Large Language Model Induced Task-Oriented Dialogue Systems Through Look-Forward Motivated Goals., Zhiyuan Hu, Yue Feng, Yang Deng, Zekun Li, See-Kiong Ng, Anh Tuan Luu, Bryan Hooi.

• ACM TOIS 2020 airwise Link Prediction Model for Out of Vocabulary Knowledge Base Entities, Richong Zhang, Samuel Mensah, Fanshuang Kong, Zhiyuan Hu, Yongyi Mao, Xudong Liu

• WWW 2019 A Neural Bag-of-Words Modelling Framework for Link Prediction in Knowledge Bases with Sparse Connectivity, Fanshuang Kong, Richong Zhang, Hongyu Guo, Samuel Mensah, Zhiyuan Hu, and Yongyi Mao

• AAAI 2019 Generating Chinese Ci with Designated Metrical Structure, Richong Zhang, X. Liu, X. Chen, Zhiyuan Hu, Zhaoqing Xu, and Yiyong Mao

🎖 Honors and Awards

• NUS President’s Graduate Fellowship (PGF)

📖 Experience

• 2023.01 - Now, PhD Student, Institute of Data Science/School of Computing, National University of Singapore.
• 2022.09 - 2023.04, Research Visitor, UCL WI/AI Centre, University College London.
• 2017.07 - 2022.09, Research Intern and R & D enginner, Big Data Big Brain, Beihang University, Beijing

💬 Invited Talks

• 2023.12, MAgIC: Investigation of Large Language Model Powered Multi-Agent in Cognition, Audaptabiulity, Ratiuonality and Cuollaboration, AgentX
• 2023.12, Techniques in Longtext Generation, Docnote
• 2023.08, Can LLMs Express Their Uncertainty?, University of Ottawa
• 2023.02, The latest Development of Language Model, Beihang Unviersity

Services

• Student Chair (2023-2024) NUS IDS NLP SIG
• Organizator of “AAAI-2019 and AAAI-2022 Chinese Seminar”
• Reviewer: ACL 2022 - Now, EMNLP 2022-Now, AACL2022-Now, COLING 2022 - Now, SIGIR23, KDD23, ARR from Dec 2023 - Now, NeurIPS 2024
• TA: CS3244 Machine Learning, CS5228 Knowledge Discovery and Data Mining

Resource

• Tips for Research (link). Quite useful material concluded by my supervisor.