Teng Shi

Teng Shi

Ph.D. Candidate at Gaoling School of Artificial Intelligence, Renmin University of China, focusing on LLM4Rec and Generative Recommendation.

I am a fourth-year Ph.D. student at the Gaoling School of Artificial Intelligence, Renmin University of China, advised by Prof. Jun Xu and Prof. Xiao Zhang. My research focuses on Large Language Models for Recommendation (LLM4Rec), generative recommendation, and generative search.

💻 Internships

  • 2026.06 - Present, Alistar Algorithm Intern, Alibaba (Taobao & Tmall Group).
  • 2026.03 - 2026.05, Kstar Algorithm Intern, OneRec Team, Kuaishou Inc.
  • 2023.08 - 2025.07, Research Intern, Kuaishou Inc.
  • 2022.03 - 2023.03, Research Intern, JD Inc.

📝 Publications

(* denotes Equal Contribution)

  • OneReason Technical Report | Core Contributor | Paper

  • LLaDA-Rec: Discrete Diffusion for Parallel Semantic ID Generation in Generative Recommendation

    (Arxiv) | Teng Shi, Chenglei Shen, Weijie Yu, Shen Nie, Chongxuan Li, Xiao Zhang, Ming He, Yan Han, Jun Xu | Paper

  • UniSAR: Modeling User Transition Behaviors between Search and Recommendation

    (SIGIR 2024, CCF A) | Teng Shi, Zihua Si, Jun Xu, Xiao Zhang, Xiaoxue Zang, Kai Zheng, Dewei Leng, Yanan Niu, Yang Song | Paper

  • Retrieval Augmented Generation with Collaborative Filtering for Personalized Text Generation

    (SIGIR 2025, CCF A) | Teng Shi, Jun Xu, Xiao Zhang, Xiaoxue Zang, Kai Zheng, Yang Song, Han Li | Paper

  • Mining Informative Interests via Latent Cross Reasoning for Search Enhanced Recommendation

    (SIGIR 2026, CCF A) | Teng Shi, Weicong Qin, Weijie Yu, Xiao Zhang, Ming He, Jianping Fan, Jun Xu | Paper

  • Benefit from Rich: Tackling Search Interaction Sparsity in Search Enhanced Recommendation

    (CIKM 2025, CCF B) | Teng Shi, Weijie Yu, Xiao Zhang, Ming He, Jianping Fan, Jun Xu | Paper

  • GenSAR: Unifying Balanced Search and Recommendation with Generative Retrieval

    (RecSys 2025, CCF B) | Teng Shi, Jun Xu, Xiao Zhang, Xiaoxue Zang, Kai Zheng, Yang Song, Enyun Yu | Paper

  • Model-Agnostic Causal Embedding Learning for Counterfactually Group-Fair Recommendation

    (TKDE 2024, CCF A) | Xiao Zhang*, Teng Shi*, Jun Xu, Zhenhua Dong, Jirong Wen (Co-first authors (student)) | Paper

  • Disentangling from Collaborative and Semantic Views: Graph Collaborative Filtering for Q&A Recommendation

    (SIGIR 2026, CCF A) | Changshuo Zhang*, Teng Shi*, Xiao Zhang, Yanping Zheng, Ruobing Xie, Qi Liu, Jun Xu, Jirong Wen | Paper

  • PrLM: Learning Explicit Reasoning for Personalized RAG via Contrastive Reward Optimization

    (CIKM 2025, CCF B) | Kepu Zhang*, Teng Shi*, Weijie Yu, Jun Xu | Paper

  • Think before recommend: Unleashing the latent reasoning power for sequential recommendation

    (TKDE, CCF A) | Jiakai Tang, Sunhao Dai, Teng Shi, Jun Xu, Xu Chen, Wen Chen, Wu Jian, Yuning Jiang | Paper

  • Bringing Model Editing to Generative Recommendation in Cold-Start Scenarios

    (SIGIR 2026, CCF A) | Chenglei Shen, Teng Shi, Weijie Yu, Xiao Zhang, Jun Xu| Paper

  • StyliTruth : Unlocking Stylized yet Truthful LLM Generation via Disentangled Steering

    (ICLR 2026, CCF A) | Chenglei Shen, Zhongxiang Sun, Teng Shi, Xiao Zhang, Jun Xu | Paper

  • Similarity = Value? Consultation Value Assessment and Alignment for Personalized Search

    (EMNLP 2025, CCF B) | Weicong Qin, Yi Xu, Weijie Yu, Teng Shi, Chenglei Shen, Ming He, Jianping Fan, Xiao Zhang, Jun Xu | Paper

  • SAQRec: Aligning Recommender Systems to User Satisfaction via Questionnaire Feedback

    (CIKM 2024, CCF B) | Kepu Zhang, Teng Shi, Sunhao Dai, Xiao Zhang, Yinfeng Li, Jing Lu, Xiaoxue Zang, Yang Song, Jun Xu | Paper

  • Test-Time Alignment with State Space Model for Tracking User Interest Shifts in Sequential Recommendation

    (RecSys 2025, CCF B) | Changshuo Zhang, Xiao Zhang, Teng Shi, Jun Xu, Jirong Wen | Paper

  • A survey of controllable learning: Methods and applications in information retrieval

    (FCS 2025, CCF B) | Chenglei Shen, Xiao Zhang, Teng Shi, Changshuo Zhang, Guofu Xie, Jun Xu | Paper

  • Modeling Domain and Feedback Transitions for Cross-Domain Sequential Recommendation

    (Arxiv) | Changshuo Zhang*, Teng Shi*, Xiao Zhang, Qi Liu, Ruobing Xie, Jun Xu, Jirong Wen | Paper

📖 Educations

  • 2022.09 - Present, PhD Candidate. Gaoling School of Artificial Intelligence, Renmin University of China.
  • 2018.09 - 2022.06, Bachelor of Computer Science. School of Computer Science, Beijing Jiaotong University.