Researcher · Learner · Collaborator
I study how Large Language Models can help us understand and improve Generative Recommendation.
I am currently a PhD candidate of the Department of Computing, The Hong Kong Polytechnic University, under the supervision of Prof. Wenqi Fan and Prof. Qing Li. My research interest covers Recommender Systems, Smart Cities, Large Language Models, Agent Reasoning. I have authored and co-authored over 20 innovative papers, most of them have been published in top journals (e.g., IEEE TKDE, IEE TITS, and ACM TOIS) and conferences (e.g., ICLR, WWW, and KDD).
01 / Overview
Towards autonomous recommendation agents.
ContRec represents users&items as latent vector representations using a not-quantized tokenizer and leverages the exceptional continuous-valued generation capability of diffusion models to operate within continuous spaces and generate implicit user preferences conditioned on the reasoning content of LLMs. Paper: https://arxiv.org/abs/2504.12007
A LLM-based Recommender System with user&item Tokenizers and a generative retrieval paradigm. TokenRec consists of the masked vector-quantized tokenizer with a K-way encoder for item ID tokenization and the generative retrieval paradigm for recommendation generation. Paper: https://arxiv.org/abs/2406.10450
A real-world dataset (Shenzhen, China) for EV-related research, e.g., spatiotemporal prediction and urban energy management. Repo: https://github.com/IntelligentSystemsLab/ST-EVCDP
02 / Selected work
HD-Prot: A Protein Language Model for Joint Sequence-Structure Modeling with Continuous Structure Tokens
Zhou Yi, Haohao Qu, Yunqing LIU, Shanru Lin, Le Song, Wenqi Fan
Atomic Intent Reasoning: Bringing LLM Semantics to Industrial Cross-Domain Recommendations
Zhuohang Jiang, Yuxin Chen, Shijie Wang, Haohao Qu, Zhou Jindong, Wenqi Fan, Li Qing, Dongxu Liang, Jun Wang
Diffusion Generative Recommendation with Continuous Tokens
Haohao Qu, Shanru Lin, Yujuan Ding, Yiqi Wang, and Wenqi Fan