Xiang Liu

Xiang Liu (εˆ˜ηΏ”)

PhD Student in Data Science and Analytics

Hong Kong University of Science and Technology (Guangzhou)

Pronouns: he/him

πŸ‘‹ About Me

I am a PhD student in Data Science and Analytics (DSA) Thrust at the Hong Kong University of Science and Technology (Guangzhou) advised by Prof. Xiaowen Chu and Prof. Xuming HU. I have been a research intern at HKUST, working with Prof. Tong Zhang. Prior to HKUST(GZ), I graduated from HKU with an M.S. in Computer Science and GMU with B.S. in Computer science.

🌱 What's New

New!

One paper accepted by AAAI 2024 Oral !!

Selected as the Top Reviewer of NeurIPS 2024 for both main and D&B tracks

πŸŒ‹ Research Interests

My main research focuses on natural language processing and machine learning. I am particularly interested in efficient LLMs and Agent. My goal is to build LLMs that can be a daily human assistant.

πŸ“œ Selected Publications

ParZC: Parametric Zero-Cost Proxies for Efficient NAS

Peijie Dong*, Lujun Li*, Xinglin Pan, Zimian Wei, Xiang Liu, Qiang Wang, Xiaowen Chu

AAAI 2024. Oral Award.

LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning

Rui Pan*, Xiang Liu*, Shizhe Diao, Renjie Pi, Jipeng Zhang, Chi Han, Tong Zhang

NeurIPS 2024

LongGenBench: Long-context Generation Benchmark

Xiang Liu, Peijie Dong, Xuming Hu, Xiaowen Chu

EMNLP Findings 2024

Should We Really Edit Language Models? On the Evaluation of Edited Language Models

Qi Li*, Xiang Liu*, Zhenheng Tang, Peijie Dong, Zeyu Li, Xinglin Pan, Xiaowen Chu

NeurIPS 2024

Active prompting with chain-of-thought for large language models

Shizhe Diao*, Pengcheng Wang*, Yong Lin, Rui Pan, Xiang Liu, Tong Zhang

ACL 2024

πŸ“ Preprints

ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference

Xiang Liu, Zhenheng Tang, Peijie Dong, Zeyu Li, Bo Li, Xuming Hu, Xiaowen Chu

arXiv preprint

Can LLMs Maintain Fundamental Abilities under KV Cache Compression?

Xiang Liu, Zhenheng Tang, Hong Chen, Peijie Dong, Zeyu Li, Xiuze Zhou, Bo Li, Xuming Hu, Xiaowen Chu

arXiv preprint

πŸ”¬ Research Experience

HKUST(GZ)

09/2023–Present

Ph.D. student, supervised by Prof. Xiaowen Chu and Prof. Xuming HU

HKUST

12/2022–08/2023

Research Intern, supervised by Prof. Tong Zhang

Baidu Research Cognitive Computing Lab

12/2021–06/2022

Research Intern, supervised by Mingming Sun

πŸ’¬ Academic Service

Conference Reviewer: ICML2025, ICLR 2025, NeurIPS 2024 (Top Reviewer), ACL (2024-2025), EMNLP (2023 - 2025)

Journal Reviewer: TMLR

πŸ€— Miscellaneous Interests