Xu Han

Xu Han

Auto-generated profile, based on publicly available information

Xu Han

Department of Computer Science and Technology, Tsinghua University, Beijing, China

Research Focus & Metrics

Academic Career Length

23Years (2004-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2022 in AI Open
Verified
Journal Article
Open access
XHXu Han
Xu Han
WZWeilin Zhao
Weilin Zhao
NDNing Ding
Ning Ding
ZLZhiyuan Liu
Zhiyuan Liu
MSMaosong Sun
Maosong Sun

24 December 2024 in ACM Computing Surveys
Verified
Journal Article
Open access
YQYujia Qin
Yujia Qin
SHShengding Hu
Shengding Hu
YLYankai Lin
Yankai Lin
WCWeize Chen
Weize Chen
NDNing Ding
Ning Ding
MSMaosong Sun
Maosong Sun
Humans possess an extraordinary ability to create and utilize tools. With the advent of foundation models, artificial intelligence systems have the potential to be equally adept in tool use as humans. This paradigm, which is dubbed as tool learning with foundation models , combines the strengths of tools and foundation models to achieve enhanced accuracy, efficiency, and automation in problem-solving. This article presents a systematic investigation and comprehensive review of tool learning. We first introduce the background of tool learning, including its cognitive origins, the paradigm shift of foundation models, and the complementary roles of tools and models. Then we recapitulate existing tool learning research and formulate a general framework: starting from understanding the user instruction, models should learn to decompose a complex task into several subtasks, dynamically adjust their plan through reasoning, and effectively conquer each sub-task by selecting appropriate tools. We also discuss how to train models for improved tool-use capabilities and facilitate generalization in tool learning. Finally, we discuss several open problems that require further investigation, such as ensuring trustworthy tool use, enabling tool creation with foundation models, and addressing personalization challenges. Overall, we hope this article could inspire future research in integrating tools with foundation models.

1 January 2021 in AI Open
Verified
Journal Article
Open access
ZZZhengyan Zhang
Zhengyan Zhang
XHXu Han
Xu Han
HZHao Zhou
Hao Zhou
PKPei Ke
Pei Ke
YGYuxian Gu
Yuxian Gu
MSMaosong Sun
Maosong Sun

6 November 2025 in Nature Machine Intelligence
Verified
Journal Article
Open access
PDF file
CXChaojun Xiao
Chaojun Xiao
JCJie Cai
Jie Cai
WZWeilin Zhao
Weilin Zhao
BLBiyuan Lin
Biyuan Lin
GZGuoyang Zeng
Guoyang Zeng
MSMaosong Sun
Maosong Sun
Large language models (LLMs) have emerged as a milestone in artificial intelligence. The scaling law indicates that the performance of LLMs can continually improve as the model size increases, which poses challenges for training and deployment. Despite numerous efforts to improve LLM efficiency, there is no general consensus on development trends and evaluation metrics for efficiency of LLMs with different scales. To address this tension between model performance and efficiency, we introduce the concept of capability density as a metric to evaluate the quality of the LLMs and describe the trend of LLMs in terms of both effectiveness and efficiency. Intuitively, capability density can be understood as the capability contained within each unit of model parameters. Capability density provides a unified framework for assessing both model performance and efficiency. Here we show an empirical observation, called the ‘densing law’, that the capability density of LLMs grows exponentially over time. More specifically, using widely used benchmarks for evaluation, the maximum capability density of open-source LLMs doubles approximately every 3.5 months. This reveals that both parameter requirements and inference costs of LLMs for achieving equivalent performance decrease exponentially, offering insights for efficient LLM development strategies.

1 January 2025
Verified
Conference Paper
Open access
PDF file
SASun Ao
Sun Ao
WZWeilin Zhao
Weilin Zhao
XHXu Han
Xu Han
Cheng YangCheng Yang
Cheng Yang
XZXinrong Zhang
Xinrong Zhang
MSMaosong Sun
Maosong Sun
Sun Ao, Weilin Zhao, Xu Han, Cheng Yang, Xinrong Zhang, Zhiyuan Liu, Chuan Shi, Maosong Sun. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

30 May 2024 in IEEE/ACM Transactions on Audio, Speech, and Language Processing
Verified
Journal Article
Closed access
WCWeize Chen
Weize Chen
XHXu Han
Xu Han
YLYankai Lin
Yankai Lin
KHKaichen He
Kaichen He
RXRuobing Xie
Ruobing Xie
MSMaosong Sun
Maosong Sun
In recent years, we have witnessed significant improvements in pre-trained language models (PLM) brought about by the scaling of parameter sizes and data amounts. However, this also brings high computational and storage costs. In this paper, we present a new direction to improve PLMs without scaling parameters and data: adopting a geometric feature space that is more suitable for encoding the intrinsic structured features of text. Although text is generally considered unstructured data, it possesses rich intrinsic structured features that signify syntactic and semantic relationships. Leveraging these structured features is vital for text understanding. Given that structured features are better encoded in hyperbolic spaces than in the Euclidean spaces used by conventional PLMs, we propose that PLMs should operate entirely within hyperbolic spaces. Our experiments demonstrate the superiority of hyperbolic PLMs over Euclidean PLMs across a wide variety of tasks, using the same parameter and data settings. This suggests that altering the geometry of model representation is a promising direction for model enhancement. The code is released at https://github.com/thunlp/hyperbolic_llm