张岸

邮 件：an_zhang@ustc.edu.cn

所属单位：人工智能与数据科学学院

个人主页： https://anzhang314.github.io/

实验室主页：https://alphalab-ustc.github.io/index.html

主要研究方向：生成式人工智能，大模型智能体，个性化大模型，大模型安全等。

        张岸，特任教授，2016年获得东南大学数学院本科学位，2021年获得新加坡国立大学统计和数据科学学院博士学位，2021年到2024年在新加坡国立大学计算机科学学院担任研究员，2022-2023年担任新加坡SEA AI Lab双聘研究员，2025年回到中国科学技术大学任教，担任特任教授，博导。主要研究领域为生成模型、大模型驱动的智能体、可信人工智能，特别关注于智慧校园、大模型安全、以及个性化场景，致力于下一代通用人工智能模型的关键能力与性质研究。相关工作在NeurIPS、ICLR、ICML、WWW、KDD、SIGIR、TOIS、TPAMI等顶级国际会议和期刊发表录用长文30余篇，其中超过3篇论文入选了最高引和最具影响力榜单，根据谷歌学术网统计，截止2025年10月，引用三千余次，H-Index指数为25，荣获2025年 Web领域女性新星奖（Rising Stars of Women in Web Award）。

教授课程：

1. 生成式人工智能概述

2. 人工智能与机器学习基础

近两年代表论著：

Generative Recommendation:

•  Xiaoyu Kong, Leheng Sheng, Junfei Tan, Yuxin Chen, Jiancan Wu, An Zhang, Xiang Wang, Xiangnan He. MiniOneRec: An Open-Source Framework for Scaling Generative Recommendation. Arxiv 2025.

•  Guoqing Hu, An Zhang*, Shuchang Liu, Wenyu Mao, Jiancan Wu, Xun Yang, Xiang Li, Lantao Hu, Han Li, Kun Gai, Xiang Wang. Fading to Grow: Growing Preference Ratios via Preference Fading Discrete Diffusion for Recommendation. NeurIPS 2025.  

•  Yingzhi He, Xiaohao Liu, An Zhang*, Yunshan Ma, Tat-Seng Chua. LLM2Rec: Large Language Models Are Powerful Embedding Models for Sequential Recommendation. KDD 2025.

•  Guoqing Hu, An Zhang*, Shuo Liu, Zhibo Cai, Xun Yang, Xiang Wang. AlphaFuse: Learn ID Embeddings for Sequential Recommendation in Null Space of Language Embeddings. SIGIR 2025.

•  Leheng Sheng, An Zhang*, Yi Zhang, Yuxin Chen, Xiang Wang, Tat-Seng Chua. Language Representations Can be What Recommenders Need: Findings and Potentials. ICLR 2025.

•  Shuo Liu, An Zhang*, Guoqing Hu, Hong Qian, Tat Seng Chua. Preference diffusion for recommendation. ICLR 2025.

•  Yuxin Chen, Junfei Tan, An Zhang*, Zhengyi Yang, Leheng Sheng, Enzhi Zhang, Xiang Wang, Tat-Seng Chua. On Softmax Direct Preference Optimization for Recommendation. NeurIPS 2024.

•  An Zhang, Yuxin Chen, Leheng Sheng, Xiang Wang, Tat-Seng Chua. On Generative Agents in Recommendation. SIGIR 2024.

LLM Reasoning/Agentic:

•  Leheng Sheng, An Zhang*, Zijian Wu, Weixiang Zhao, Changshuo Shen, Yi Zhang, Xiang Wang, Tat-Seng Chua. On Reasoning Strength Planning in Large Reasoning Models. NeurIPS 2025.  

•  Yaorui Shi, Sihang Li, Chang Wu, Zhiyuan Liu, Junfeng Fang, Hengxing Cai, An Zhang, Xiang Wang. Search and Refine During Think: Facilitating Knowledge Refinement for Improved Retrieval-Augmented Reasoning. NeurIPS 2025.

•  Yuxin Chen, Yiran Zhao, Yang Zhang, An Zhang, Kenji Kawaguchi, Shafiq Joty, Junnan Li, Tat-Seng Chua, Michael Qizhe Shieh, Wenxuan Zhang. The Emergence of Abstract Thought in Large Language Models Beyond Any Language. NeurIPS 2025.

•  Jingnan Zheng, Han Wang, An Zhang*, Tai D. Nguyen, Jun Sun, Tat-Seng Chua. ALI-Agent: Assessing LLMs' Alignment with Human Values via Agent-based Evaluation. NeurIPS 2024.

LLM Safety:

•  Jingnan Zheng, Xiangtian Ji, Yijun Lu, Chenhang Cui, Weixiang Zhao, Gelei Deng, Zhenkai Liang, An Zhang*, Tat-Seng Chua. RSafe: Incentivizing proactive reasoning to build robust and adaptive LLM safeguards. NeurIPS 2025.

•  Chenhang Cui, Gelei Deng, An Zhang*, Jingnan Zheng, Yicong Li, Lianli Gao, Tianwei Zhang, Tat-Seng Chua. Safe + Safe = Unsafe? Exploring How Safe Images Can Be Exploited to Jailbreak

 Large Vision-Language Models. NeurIPS 2025.

•  Chenhang Cui, An Zhang*, Yiyang Zhou, Zhaorun Chen, Gelei Deng, Huaxiu Yao, Tat-Seng Chua. Fine-Grained Verifiers: Preference Modeling as Next-token Prediction in Vision-Language Alignment. ICLR 2025.

•  Jingnan Zheng, Jiahao Liu, An Zhang*, Jun Zeng, Ziqi Yang, Zhenkai Liang, Tat-Seng Chua. MaskDroid: Robust Android malware detection with masked graph representations. ASE 2024.