Qizhi Pei (裴启智 in Chinese) is currently a fourth year Ph.D. student at the ALOHA group of Gaoling School of Artificial Intelligence (GSAI) in Renmin University of China (RUC), supervised by Prof. Rui Yan. He got the B.S. degree from School of Computer Science and Technology, University of Science and Technology of China (USTC) in 2022. He currently is an intern of OpenDataLab in Shanghai Artificial Intelligent Laboratory, mentored by Dr. Lijun Wu. He is the core contributor of OpenDataArena. His researches focus on

• AI4science, including scientific foundation model (BioT5, BioT5+, 3D-MolT5, NatureLM) and biomolecule interaction (FABind, FABind+, kNN-DTA, SSM-DTA)
• Data-centric LLMs, including mathematical reasoning (MathFusion, LEMMA, MetaLadder, REST) and data synthesis (Middo, GRA)

🔥 News

• 2025.09:  🔥🔥 ScaleDiff is made public.
• 2025.09:  🎉🎉 Caco is accepted by NeurIPS 2025. Congrats to Honglin!
• 2025.08:  🎉🎉 MetaLadder and Middo is accepted by EMNLP 2025. Congrats to Honglin and Zinan!
• 2025.08:  🔥🔥 We release OpenDataArena – a fair, open, and transparent arena for data.
• 2025.07:  🔥🔥 REST is made public. See project page for more information.
• 2025.05:  🎉🎉 MathFusion is accepted by ACL 2025 (main). Thanks for all collaborators!
• 2025.02:  🔥🔥 NatureLM is made public. See project page for more information.
• 2025.01:  🎉🎉 3D-MolT5 is accepted by ICLR 2025. Thanks for all collaborators!
• 2024.11:  🎉🎉 FABind+ is accepted by KDD 2025. Congrats to Kaiyuan!
• 2024.07:  🎉🎉 The enhanced version of BioT5+ achieves remarkable results in Language + Molecule @ ACL2024 Workshop/Competition:
  • 🥇 1st Place in the Text-based Molecule Generation Track.
  • 🥈 2nd Place in the Molecular Captioning Track.
  • 🎤 Oral presentation in the workshop.

📝 AI4Science

• EMNLP 2023: BioT5: Enriching Cross-modal Integration in Biology with Chemical Knowledge and Natural Language Associations, Qizhi Pei, Wei Zhang, Jinhua Zhu, Kehan Wu, Kaiyuan Gao, Lijun Wu, Yingce Xia, Rui Yan, | | (>20W downloads)

• ACL 2024 (Findings): BioT5+: Towards Generalized Biological Understanding with IUPAC Integration and Multi-task Tuning, Qizhi Pei, Lijun Wu, Kaiyuan Gao, Xiaozhuan Liang, Yin Fang, Jinhua Zhu, Shufang Xie, Tao Qin, Rui Yan | |

• ICLR 2025: 3D-MolT5: Leveraging Discrete Structural Information for Molecule-Text Modeling, Qizhi Pei, Lijun Wu, Kaiyuan Gao, Jinhua Zhu, Rui Yan | |

• NeurIPS 2023: FABind: Fast and Accurate Protein-Ligand Binding, Qizhi Pei (co-first author), Kaiyuan Gao, Lijun Wu, Jinhua Zhu, Yingce Xia, Shufang Xie, Tao Qin, Kun He, Tie-Yan Liu, Rui Yan | Project Page | |

• Language + Molecules @ ACL 2024 Workshop (Oral): Enhanced BioT5+ for Molecule-Text Translation: A Three-Stage Approach with Data Distillation, Diverse Training, and Voting Ensemble, Qizhi Pei, Lijun Wu, Kaiyuan Gao, Jinhua Zhu, Rui Yan
  1. 🥇 1st Place in the Text-based Molecule Generation Track.
  2. 🥈 2nd Place in the Molecular Captioning Track.

• CIKM 2024: Exploiting Pre-trained Models for Drug Target Affinity Prediction with Nearest Neighbors, Qizhi Pei (co-first author), Lijun Wu, Zhenyu He, Jinhua Zhu, Yingce Xia, Shufang Xie, Rui Yan

• Briefings in Bioinformatics 2023: SSM-DTA: Breaking the Barriers of Data Scarcity in Drug-Target Affinity Prediction, Qizhi Pei, Lijun Wu, Jinhua Zhu, Yingce Xia, Shufang Xie, Tao Qin, Haiguang Liu, Tie-Yan Liu, Rui Yan |

• KDD 2025: FABind+: Enhancing Molecular Docking through Improved Pocket Prediction and Pose Generation
  Kaiyuan Gao, Qizhi Pei, Jinhua Zhu, Tao Qin, Kun He, Lijun Wu |

• Nature Communications 2024: TamGen: drug design with target-aware molecule generation through a chemical language model, Kehan Wu, Yingce Xia, Pan Deng, Renhe Liu, Yuan Zhang, Han Guo, Yumeng Cui, Qizhi Pei, … , Tao Qin, Tie-Yan Liu |

• Preprint: Leveraging Biomolecule and Natural Language through Multi-Modal Learning: A Survey, Qizhi Pei, Lijun Wu, Kaiyuan Gao, Jinhua Zhu, Yue Wang, Zun Wang, Tao Qin, Rui Yan |

• Preprint: Nature Language Model: Deciphering the Language of Nature for Scientific Discovery, Yingce Xia, Peiran Jin, Shufang Xie, Liang He, Chuan Cao, … , Qizhi Pei, … , Tie-Yan Liu, Haiguang Liu, Tao Qin | Project | |

• Preprint Tokenizing 3D Molecule Structure with Quantized Spherical Coordinates, Kaiyuan Gao, Yusong Wang, Haoxiang Guan, Zun Wang, Qizhi Pei, John E. Hopcroft, Kun He, and Lijun Wu |

📝 LLMs

• ACL 2025: MathFusion: Enhancing Mathematic Problem-solving of LLM through Instruction Fusion, Qizhi Pei, Lijun Wu, Zhuoshi Pan, Yu Li, Honglin Lin, Chenlin Ming, Xin Gao, Conghui He, Rui Yan | |

• NeurIPS 2025: Scaling Code-Assisted Chain-of-Thoughts and Instructions for Model Reasoning, Honglin Lin, Qizhi Pei (co-first author), Xin Gao, Zhuoshi Pan, Yu Li, Juntao Li, Conghui He, Lijun Wu | |

• ACL 2025: A Strategic Coordination Framework of Small LLMs Matches Large LLMs in Data Synthesis, Xin Gao, Qizhi Pei, Zinan Tang, Yu Li, Honglin Lin, Jiang Wu, Lijun Wu, Conghui He |

• ACL 2025 (Findings): CipherBank: Exploring the Boundary of LLM Reasoning Capabilities through Cryptography Challenges, Yu Li, Qizhi Pei, Mengyuan Sun, Honglin Lin, Chenlin Ming, Xin Gao, Jiang Wu, Conghui He, Lijun Wu |

• ACL 2025 (Findings): LEMMA: Learning from Errors for MatheMatical Advancement in LLMs, Zhuoshi Pan, Yu Li, Honglin Lin, Qizhi Pei, Zinan Tang, Wei Wu, Chenlin Ming, H. Vicky Zhao, Conghui He, Lijun Wu | |

• EMNLP 2025: Middo: Model-Informed Dynamic Data Optimization for Enhanced LLM Fine-Tuning via Closed-Loop Learning, Zinan Tang, Xin Gao, Qizhi Pei, Zhuoshi Pan, Mengzhang Cai, Jiang Wu, Conghui He, Lijun Wu

• EMNLP 2025 (Findings): MetaLadder: Ascending Mathematical Solution Quality via Analogical-Problem Reasoning Transfer, Honglin Lin, Zhuoshi Pan, Yu Li, Qizhi Pei, Xin Gao, Mengzhang Cai, Conghui He, Lijun Wu | Project |

• Preprint: ScaleDiff: Scaling Difficult Problems for Advanced Mathematical Reasoning, Qizhi Pei, Zhuoshi Pan, Honglin Lin, Xin Gao, Yu Li, Zinan Tang, Conghui He, Rui Yan, Lijun Wu | |

• Preprint: Stress Testing Large Reasoning Models by Asking Multiple Problems at Once, Zhuoshi Pan, Qizhi Pei (co-first author), Yu Li, Qiyao Sun, Zinan Tang, H. Vicky Zhao, Conghui He, Lijun Wu | Project |

• Preprint: IDEAL: Data Equilibrium Adaptation for Multi-Capability Language Model Alignment, Chenlin Ming, Chendi Qu, Mengzhang Cai, Qizhi Pei, Zhuoshi Pan, Yu Li, Xiaoming Duan, Lijun Wu, Conghui He

• Preprint: Examining User-Friendly and Open-Sourced Large GPT Models: A Survey on Language, Multimodal, and Scientific GPT Models, Kaiyuan Gao, Sunan He, Zhenyu He, Jiacheng Lin, Qizhi Pei, Jie Shao, Wei Zhang |

🏆 Competitions

• Language + Molecules @ ACL 2024:
  1. 🥇 1st Place in the Text-based Molecule Generation Track.
  2. 🥈 2nd Place in the Molecular Captioning Track.
  3. 🎤 Oral presentation: Enhanced BioT5+ for Molecule-Text Translation: A Three-Stage Approach with Data Distillation, Diverse Training, and Voting Ensemble, Qizhi Pei, Lijun Wu, Kaiyuan Gao, Jinhua Zhu, Rui Yan.

• CURE-Bench @ NeurIPS 2025: 3rd place in Internal Reasoning Track.

• OGB-LSC @ NeurIPS 2022: 7th place (PhiNeurons team) in PCQM4Mv2 leaderboard.

🎖 Honors and Awards

• 2025, National Scholarship for Doctoral Students.
• 2023~2024, Doctoral Scholarship for Elite Innovative Talents of Renmin University of China.
• 2022, Excellent Graduation Thesis, USTC.
• 2022, Outstanding Undergraduate Awards, USTC.
• 2018~2021, Outstanding Student Scholarship, USTC.

💬 Academic Service

• Reviewer: NeurIPS, ACL, EMNLP, KDD, ICLR

📖 Educations

• 2022.09 - Now, Ph.D. student in the Gaoling School of Artificial Intelligence, Renmin University of China.
• 2018.09 - 2022.06, undergraduate student in the School of Computer Science and Technology, University of Science and Technology of China.

💻 Internships

• 2024.08 - now, OpenDataLab, Shanghai Artificial Intelligent Laboratory, Beijing, China
• 2023.07 - 2024.06, Microsoft Research AI4Science, Beijing, China.
• 2021.07 - 2023.01, Microsoft Research Asia, Beijing, China.