Xu Huang 黄旭

Xu Huang 黄旭

Ph.D Student of USTC

I am currently a 4th-year Ph.D. student under the advisory of Prof.Defu Lian in School of Computer Science and Technology, University of Science and Technology of China (USTC). I got my B.S. degree from University of Science and Technology of China (USTC) in 2021.

My research interest includes large language models, data mining, information retrieval, especially on recommender system. Recently my major research direction is on the LLM-driven autonomous agents. I have published several papers at the top international AI conferences with total 300+ google scholar citations .

🔥 News

  • 2024.09:  🎉🎉 Our framework and model ToolACE for enhancing tool-using ability of LLM is released in arXiv.
  • 2024.05:  🎉🎉 Our work for weak exploration to strong exploitation for LLM agents is released in arXiv.
  • 2024.04:  🎉🎉 Our method for weak exploration to strong exploitation for LLM agents is released in arXiv.
  • 2024.03:  🎉🎉 Our demo paper for the toolkit RecAI for bridging LLM and Recommendation Systems is accepted by WWW 2024. The project is released in Github.
  • 2024.02:  🎉🎉 Our survey for the planning ability of LLM agents is released in arXiv.
  • 2024.01:  🎉🎉 Our work for the data-centric multi-objective recommendation MoRec is accepted by WWW 2024, accept rate 20.2%.

📝 Publications

arXiv
sym

ToolACE: Winning the Points of LLM Function Calling

Weiwen Liu*, Xu Huang*, Xingshan Zeng*, Xinlong Hao, Shuai Yu, Dexun Li, Shuai Wang, Weinan Gan, et al.

Project

  • A data synthetic framework tailored for enhancing tool-using ability of LLMs.
  • Model; Dataset
KDD2024
sym

RecExplainer: Aligning Large Language Models for Explaining Recommendation Models

Yuxuan Lei, Jianxun Lian, Jing Yao, Xu Huang, Defu Lian, Xing Xie

Project

  • A novel approach to leverage LLMs as surrogate models for explaining black-box recommender models.
ICML2024
sym

Learning-Efficient Yet Generalizable Collaborative Filtering for Item Recommendation

Yuanhao Pu, Xiaolong Chen, Xu Huang, Jin Chen, Defu Lian, Enhong Chen

Project

  • This work proposes a new square loss RG2 for recommendation based on the approximation of the softmax loss with Taylor expansion.
  • We have studied the theoretical properties of the proposed loss in terms of generalization and consistency.
arXiv
sym

WESE: Weak Exploration to Strong Exploitation for LLM Agents

Xu Huang, Weiwen Liu, Xiaolong Chen, Xingmei Wang, Defu Lian, Yasheng Wang, Ruiming Tang, Enhong Chen

Project

  • A novel prompt-based method for LLM agents, leveraging weaker agent for exploration and stronger agent for exploitation.
WWW2024
sym

RecAI: Leveraging Large Language Models for Next-GenerationRecommender Systems

Jianxun Lian, Yuxuan Lei, Xu Huang, Jing Yao, Wei Xu, Xing Xie

Project

  • A practical toolkit designed to augmentor even revolutionize recommender systems with the advanced capabilities of Large Language Models.
  • Demo Paper
arXiv
sym

Understanding the planning of LLM agents: A survey

Xu Huang, Weiwen Liu, Xiaolong Chen, Xingmei Wang, Hao Wang, Defu Lian, Yasheng Wang, Ruiming Tang, Enhong Chen

Project

  • A survey about the planning ability of LLM agents.
WWW 2024
sym

A Data-Centric Multi-Objective Learning Framework for Responsible Recommendation Systems

Xu Huang, Jianxun Lian, Hao Wang, Defu Lian, Xing Xie

Project

  • A data-centric framework for multi-objective learning in recommendation systems.
  • Code
arXiv
sym

Recommender AI Agent: Integrating Large Language Models for Interactive Recommendations

Xu Huang, Jianxun Lian, Yuxuan Lei, Jing Yao, Defu Lian, Xing Xie

Project

  • A framework to build an interactive recommendation agent with LLM
  • Code
WWWJ
sym

When large language models meet personalization: Perspectives of challenges and opportunities

Jin Chen, Zheng Liu, Xu Huang, Chenwang Wu, Qi Liu, Gangwei Jiang, Yuanhao Pu, Yuxuan Lei, Xiaolong Chen, Xingmei Wang, Defu Lian, Enhong Chen

Project

  • A survey to summarize the combination of large language models and personlization systems
SIGIR 2023
sym

RecStudio: Towards a Highly-Modularized Recommender System

Defu Lian, Xu Huang, Xiaolong Chen, Jin Chen, Xingmei Wang, Yankai Wang, Haoran Jin, Rui Fan, Zheng Liu, Le Wu, Enhong Chen

Project

  • A modularized recommender system library RecStudio was developped and released to public
  • Project homepage
WWW 2023
sym

Cooperative Retriever and Ranker in Deep Recommenders

Xu Huang, Defu Lian, Jin Chen, Zheng Liu, Xing Xie, Enhong Chen

Project

  • An adaptive hard negative sampler was introduced to enhance the ranker
  • An sampling based KL divergence was proposed to enhance the retriever
WWW 2022
sym

Fast variational autoencoder with inverted multi-index for collaborative filtering

Jin Chen, Defu Lian, Binbin Jin, Xu Huang, Kai Zhang, Enhong Chen

Project

  • An adaptive negative sampler was proposed to training VAE efficiently

⚙️ Projects

  • ToolACE: Large Language Models tailored for functional-calling (or tool-using) tasks.
  • RecAI: A project aims to bridge this gap by investigating various strategies to integrate LLMs into recommender systems.
  • RecFM: A project aims to build foundation models for recommendation systems.
  • RecStudio: A modularized and unified library for recommendation system based on PyTorch.
  • UniRec: An easy-to-use, lightweight, and scalable implementation of recommender systems.

🎖 Honors and Awards

  • Stars of Tomorrow Award, Microsoft Research Asia, 2023.10
  • National Scholarship, 2023.10
  • USTC Academic Scholarship, 2021.09, 2022.09, 2023.09, 2024.09
  • USTC Excellent Student Prize, 2017.09, 2018.09, 2019.09
  • National Encouragement Scholarship, 2018.09
  • Shizhang Bei Talent class Scholarship, 2017.09

📖 Educations

💻 Internships

⏳ Professional Services

Program Committee Members

📃 Curriculum Vitae

I am a 2026 graduate seeking employment opportunities. Please do not hesitate to contact me via email if you have any suitable positions available. Contact me: xuhuangcs@mail.ustc.edu.cn.

📈 Pageviews