Keqin Bao

Keqin Bao

Ph.D. Candidate at USTC

About me

I am a fourth-year Ph.D. student in the University of Science and Technology of China, advised by Prof. Xiangnan He and Fuli Feng. Previously, I received my bachelor’s degree from the Elite College at Harbin Institute of Technology in 2021. I expect to graduate in June 2026. I was awarded the National Scholarship for three years.

My research interests are in improving the general reasoning abilities of foundational LLMs, LLMs for recommendation and scaling reinforcement reasoning.

  • General Reasoning of Foundational LLMs: Focusing on enhancing the general reasoning abilities of LLMs during the pre-training and post-training phase, including STEM, code, and logical reasoning, as in Qwen2.5 Series, Qwen3 Series, QwQ.

  • LLMs for Recommendation: Exploring the application of LLMs in recommendations, including user modeling and dynamically adapting to users’ new interests, as in TallRec, BigRec, D^3, RecICL.

  • Scaling Reinforcement Learning: Automating the scaling of RL question-answer pairs through code-related problems to enhance general reasoning capabilities, as in TeaR and MTR-Bench.

🔥 News

  • 2025-05: Three papers accepted to ACL 2025
  • 2025-05: Qwen3 Technical Report is officially out!
  • 2025-04: QwQ-32B is released!
  • 2025-04: Two papers and one tutorial accepted to SIGIR 2025
  • 2024-12: QwQ-32B-Preview is released!
  • 2024-12: One paper accepted to TKDE
  • 2024-12: Qwen2.5 Technical Report is officially out!
  • 2024-10: Two papers accepted to EMNLP 2024

🚀 Selected Publications

(*=equal contribution)

  • Qwen3 Technical Report. Core Contributor [paper]
  • Qwen2.5 Technical Report. Core Contributor [paper]
  • Xiaoyuan Li, Keqin Bao, Yubo Ma, Moxin Li, Wenjie Wang, Rui Men, Yichang Zhang, Fuli Feng, Dayiheng Liu, Junyang Lin. MTR-Bench: A Comprehensive Benchmark for Multi-Turn Reasoning Evaluation. [paper]
  • Keqin Bao, Nuo Chen, Xiaoyuan Li, Binyuan Hui, Bowen Yu, Fuli Feng, Junyang Lin, Xiangnan He, Dayiheng Liu. Teaching LLM to Reason: Reinforcement Learning from Algorithmic Problems without Code.
  • Keqin Bao, Jizhi Zhang, Yang Zhang, Wenjie Wang, Fuli Feng, Xiangnan He. Tallrec: An effective and efficient tuning framework to align large language model with recommendation. Cited by 500+ [paper]
  • Jizhi Zhang, Keqin Bao, Yang Zhang, Wenjie Wang, Fuli Feng, Xiangnan He. Is chatgpt fair for recommendation? evaluating fairness in large language model recommendation. Cited by 200+ [paper]
  • Keqin Bao, Jizhi Zhang, Wenjie Wang, Yang Zhang, Zhengyi Yang, Yanchen Luo, Chong Chen, Fuli Feng, Qi Tian. A bi-step grounding paradigm for large language models in recommendation systems. Cited by 100+ [paper]

📚 Publications

You can also find my articles on my Google Scholar profile.

Cited by 3K+

2025

  • Qwen3 Technical Report. Core Contributor [paper]
  • Xiaoyuan Li, Keqin Bao, Yubo Ma, Moxin Li, Wenjie Wang, Rui Men, Yichang Zhang, Fuli Feng, Dayiheng Liu, Junyang Lin. MTR-Bench: A Comprehensive Benchmark for Multi-Turn Reasoning Evaluation. [paper]
  • Shihao Cai, Chongming Gao, Yang Zhang, Wentao Shi, Jizhi Zhang, Keqin Bao, Qifan Wang, Fuli Feng. K-order Ranking Preference Optimization for Large Language Models [paper]
  • Xiaoyuan Li, Moxin Li, Rui Men, Yichang Zhang, Keqin Bao, Wenjie Wang, Fuli Feng, Dayiheng Liu, Junyang Lin. HellaSwag-Pro: A Large-Scale Bilingual Benchmark for Evaluating the Robustness of LLMs in Commonsense Reasoning [paper]
  • Jizhi Zhang, Keqin Bao, Wenjie Wang, Yang Zhang, Wentao Shi, Wanhong Xu, Fuli Feng, Tat-Seng Chua. Envisioning Recommendations on an LLM-Based Agent Platform [paper]
  • Keqin Bao, Ming Yan, Yang Zhang, Jizhi Zhang, Wenjie Wang, Fuli Feng, Xiangnan He. Real-Time Personalization for LLM-based Recommendation with Customized In-Context Learning [paper]

2024

  • Qwen2.5 Technical Report. Core Contributor [paper]
  • Shihao Cai, Jizhi Zhang, Keqin Bao, Chongming Gao, Qifan Wang, Fuli Feng, Xiangnan He. Agentic Feedback Loop Modeling Improves Recommendation and User Simulation [paper]
  • Shihao Cai, Jizhi Zhang, Keqin Bao, Chongming Gao, Fuli Feng, FLOW: A Feedback LOop FrameWork for Simultaneously Enhancing Recommendation and User Agents [paper]
  • Keqin Bao, Jizhi Zhang, Yang Zhang, Xinyue Huo, Chong Chen, Fuli Feng. Decoding Matters: Addressing Amplification Bias and Homogeneity Issue in Recommendations for Large Language Models [paper]
  • Yang Zhang, Juntao You, Yimeng Bai, Jizhi Zhang, Keqin Bao, Wenjie Wang, Tat-Seng Chua. Causality-Enhanced Behavior Sequence Modeling in LLMs for Personalized Recommendation [paper]
  • Shihao Cai, Keqin Bao, Hangyu Guo, Jizhi Zhang, Jun Song, Bo Zheng. GeoGPT4V: Towards Geometric Multi-modal Large Language Models with Geometric Image Generation [paper]
  • Yang Zhang, Keqin Bao, Ming Yan, Wenjie Wang, Fuli Feng, Xiangnan He. Text-like Encoding of Collaborative Information in Large Language Models for Recommendation [paper]
  • Meng Jiang, Keqin Bao, Jizhi Zhang, Wenjie Wang, Zhengyi Yang, Fuli Feng, Xiangnan He. Item-side fairness of large language model-based recommendation system [paper]

2023

  • Keqin Bao, Jizhi Zhang, Yang Zhang, Wenjie Wang, Fuli Feng, Xiangnan He. Tallrec: An effective and efficient tuning framework to align large language model with recommendation. [paper]
  • Jizhi Zhang, Keqin Bao, Yang Zhang, Wenjie Wang, Fuli Feng, Xiangnan He. Is chatgpt fair for recommendation? evaluating fairness in large language model recommendation. [paper]
  • Yang Zhang, Fuli Feng, Jizhi Zhang, Keqin Bao, Qifan Wang, Xiangnan He. Collm: Integrating collaborative embeddings into large language models for recommendation [paper]
  • Keqin Bao, Jizhi Zhang, Wenjie Wang, Yang Zhang, Zhengyi Yang, Yanchen Luo, Chong Chen, Fuli Feng, Qi Tian. A bi-step grounding paradigm for large language models in recommendation systems [paper]

📝 Services

  • Reviewer for
    • ACL 2024, 2025
    • EMNLP 2024
    • SIGIR 2025
    • RecSys 2024, 2025
    • TOIS, TORS, TKDD, TKDE

🎓 Education

  • University of Science and Technology of China
    Ph.D. in Computer Science (2021 - present)
    Advisor: Prof. Xiangnan He and Fuli Feng

  • Harbin Institute of Technology
    B.E. in Computer Science (Elite College) (2017 - 2021)

🏆 Honors and Awards

  • National Scholarship 2018, 2019, 2020
  • ACM-ICPC Asia East Continent Finals, Gold Medal 2019
  • ACM-ICPC Asia egional Contest Nanjing, Gold Medal 2019
  • Provincial-Level Merit Student 2018-2019
  • The ACM-ICPC Asia Regional Contest Silver Medal * 3