An Zhang, USTC, University of Science and Technology of China

Professor
Alpha Lab
School of Artificial Intelligence and Data Science
University of Sicence and Technology of China (USTC)

✉ Email: an_zhang at ustc.edu.cn
• Google Scholar Page • OpenReview Profile

Biography

I am currently a Professor at University of Science and Technology of China (USTC), where I lead the Alpha Lab. Prior to that, I was a postdoctoral research fellow in NExT++ Lab, National University of Singapore, working with Prof. Tat-Seng Chua. I obtained my Ph.D. from the National University of Singapore in 2021 and joined USTC in 2025.
At AlphaLab, my colleagues, students, and collaborators work together to develop foundation models (large language models & diffusion models) and AI Agents, with an emphasis on understanding the capabilities and properties of next-generation general AI models. Our research is motivated by, and contributes to, real-world applications in personalization (e.g., recommender systems), education (e.g., smart campuses), and safety (e.g., LLM Safety).

Personalization
- Tutorials [WWW 2025 Generative Recommendation Models] [CIKM 2025]
- LLM as Recommender [ReRe] [NeurIPS 2024 S-DPO] [SIGIR 2024 Agent4Rec]
- LLM enhanced Recommender [SIGIR 2025 AlphaFuse] [KDD 2025 LLM2Rec] [ICLR 2025 AlphaRec]
- Diffusion as Recommender [NeurIPS 2025 PrefGrow] [ICLR 2025 PrefDiff] [iDreamRec]
Understanding and Abilitiies of Large Language Models
- Agentic [WWW 2024 Tutorial] [SIGIR 2024 Tutorial] [NeurIPS 2025 AutoRefine]
- Reasoning [NeurIPS 2025 AlphaReasoner]
- Safety [AlphaAlign] [NeurIPS 2025 SSA] [NeurIPS 2025 RSafe][AlphaSteer]
- Multimodality [ICLR 2025 FiSAO]

Prospective PhD, Master, and Intern Students

I am actively looking for highly motivated PhD students, master students, and interns (undergraduate students) to work together on the trustworthiness AI, Personalization, and LLM-empowered Agents, and their applications in real-world scenarios. Please feel free to send me your CV and transcripts, if you have interest. We are also actively looking for opportunities in research, partnership and commercialization in exciting AI projects.

News and Highlights

2025/09 Seven papers have been accepted by NeurIPS 2025! Big congrats to Guoqing Hu, Yaorui Shi, Leheng Sheng, Chenhang Cui, Jingnan Zheng, Yuxin Chen, Yu Shang and all collaborators!
Fading to Grow: Growing Preference Ratios via Preference Fading Discrete Diffusion for Recommendation .

Search and Refine During Think: Facilitating Knowledge Refinement for Improved Retrieval-Augmented Reasoning .

On Reasoning Strength Planning in Large Reasoning Models .

Safe + Safe = Unsafe? Exploring How Safe Images Can Be Exploited to Jailbreak Large Vision-Language Models .

RSafe: Incentivizing Proactive Reasoning to Build Robust and Adaptive LLM Safeguards .

The Emergence of Abstract Thought in Large Language Models Beyond Any Language .

AgentRecBench: Benchmarking LLM Agent-based Personalized Recommender Systems .
2025/06 One paper is accepted by KDD'25! Big congrats to Yingzhi He and Xiaohao Liu!
LLM2Rec: Large Language Models Are Powerful Embedding Models for Sequential Recommendation .
2025/04 One paper is accepted by SIGIR'25! Big congrats to Guoqing Hu!
AlphaFuse: Learn ID Embeddings for Sequential Recommendation in Null Space of Language Embeddings .
2025/01 Three papers are accepted by ICLR'25! Congratulations to Leheng Sheng, Chenhang Cui, Shuo Liu and all collaborators!
Language Representations Can be What Recommenders Need: Findings and Potentials (Oral) .

Fine-Grained Verifiers: Preference Modeling as Next-token Prediction in Vision-Language Alignment .

Preference Diffusion for Recommendation .
2024/12 Four papers are accepted by NeurIPS'24! Big congrats to Yuxin Chen, Xiaoyu Kong, Junfeng Fang, Jingnan Zheng and all collaborators!
On Softmax Direct Preference Optimization for Recommendation .

Customizing Language Models with Instance-wise LoRA for Sequential Recommendation .

Towards Neuron Attributions in Multi-Modal Large Language Models .

ALI-Agent: Assessing LLMs' Alignment with Human Values via Agent-based Evaluation .
2024/08 One paper is accepted by ACL 2024! Big congrats to Zhiyuan Liu and other collaborators!
ProtT3: Protein-to-Text Generation for Text-based Protein Understanding .
2024/05 One paper is accepted by The Web Conference 2024 (WWW'24)! Big congrats to Wenchang Ma and other collaborators!
General Debiasing for Graph-based Collaborative Filtering via Adversarial Graph Dropout .
2024/07 One perspective paper and two tutorial papers are accepted by SIGIR'24 and WWW'24! Big congrats to all collaborators!
On Generative Agents in Recommendation (SIGIR 2024 Perspective Track) .

Large Language Model Powered Agents for Information Retrieval (SIGIR 2024 Tutorial) .

Large Language Model Powered Agents in the Web (WWW 2024 Companion Tutorial) .
2024/03 One paper is accepted by TOIS 2024! Thank all collaborators!
Robust Collaborative Filtering to Popularity Distribution Shift .
2023/10 One paper is accepted by EMNLP'23 Findings! Big congrats to Yaorui Shi and other collaborators!
ReLM: Leveraging Language Models for Enhanced Chemical Reaction Prediction .
2023/09 Three papers are accepted by NeurIPS'23! Big congrats to Zhiyuan Liu, Junfeng Fang, and other collaborators!
Empowering Collaborative Filtering with Principled Adversarial Contrastive Loss .

Evaluating Post-hoc Explanations for Graph Neural Networks via Robustness Analysis .

Rethinking Tokenizer and Decoder in Masked Graph Modeling for Molecules .
2023/07 Two papers are accepted by ACM MM'23! Big congrats to Yicong Li, Wei Ji, and other collaborators!
Redundancy-aware Transformer for Video Question Answering .

Online Distillation-enhanced Multi-modal Transformer for Sequential Recommendation .
2023/05 One paper is accepted by KDD'23! Big congrats to Fangfu Liu and other collaborators!
Discovering Dynamic Causal Space for DAG Structure Learning .
2023/01 One paper is accepted by WWW'23! Thank all collaborators!
Invariant Collaborative Filtering to Popularity Distribution Shift .
2023/01 One paper is accepted by ICLR'23! Thank all collaborators!
Boosting Causal Discovery via Adaptive Sample Reweighting .
2022/10 One paper is accepted by WSDM'23! Big congrats to Junfeng Fang and other collaborators!
Cooperative Explanations of Graph Neural Networks .
2022/09 One paper is accepted by NeurIPS'22! Thank all collaborators!
Incorporating Bias-aware Margins into Contrastive Loss for Collaborative Filtering .
2022/05 One paper is accepted by ICML'22! Big congrats to Sihang Li and other collaborators!
Let Invariant Rationale Discovery Inspire Graph Contrastive Learning .
2022/05 One paper is accepted by KDD'22! Big congrats to Yunshan Ma and other collaborators!
CrossCBR: Cross-view Contrastive Learning for Bundle Recommendation .
2022/04 One paper is accepted by TPAMI'22! Big congrats to Xiang Wang and other collaborators!
Reinforced Causal Explainer for Graph Neural Networks .
2022/01 One paper is accepted by ICLR'22! Big congrats to Yinxin Wu and other collaborators!
Discovering Invariant Rationales for Graph Neural Networks .

Professional Services

Program Committee member for NeurIPS and ACL; reviewer/PC for other major AI, ML, NLP and Data Mining venues including ICML, ICLR, KDD, WWW/TheWebConf, SIGIR, EMNLP, AAAI, WSDM, CVPR, ICCV, ECCV, ACM MM, as well as related workshops and journal tracks.