I am a first-year Ph.D. student at School of Artificial Intelligence, Shanghai Jiao Tong University (SAI, SJTU), jointly trained with Shanghai AI Laboratory, supervised by Dr. Lijun Wu, Dr. Conghui He, and Prof. Yanfeng Wang. I received my B.S. degree from School of Artificial Intelligence, Beijing University of Posts and Telecommunications (BUPT). I’m also a core contributor of OpenDataArena. My research interests are mainly in LLMs, VLMs and Post-training.

🔥 News

• 2026.03: We release the data curation pipeline of MMFineReason. Check out the code!
• 2026.01: The technical report of MMFineReason is released. We close the multimodal reasoning gap via open data-centric methods. Our datasets have got 20k+ downloads!
• 2025.12: The technical report of OpenDataArena is released. Thanks to all collaborators!
• 2025.09: Caco is accepted by NeurIPS 2025! We scale code-assisted CoT and instruction data to enhance LLM reasoning.
• 2025.08: MetaLadder is accepted by EMNLP 2025! As a preliminary example of test-time scaling, we enhance math reasoning by transferring analogical-problem knowledge.
• 2025.08: We release OpenDataArena – a fair, open, and transparent arena for data.
• 2025.07: We empirically explore the generalization of multi-domain reasoning data (math, code, puzzle) in RL. Check out our report!
• 2025.06: CVG-Text is accepted by ICCV 2025! We tackle cross-view geo-localization via multimodal alignment between images and natural language descriptions.
• 2025.05: Grateful to have several works accepted to ACL 2025: MathFusion, LEMMA, CipherBank, GRA. These works all focus on data synthesis and reasoning in LLMs. Thanks to all collaborators!
• 2025.01: LOKI is accepted by ICLR 2025 Spotlight. Thanks to all collaborators!
• 2024.05: ContextBLIP is accepted by Findings of ACL 2024! We propose doubly contextual alignment for contrastive image retrieval from complex descriptions.

📝 Publications

• NeurIPS 2025 Scaling Code-Assisted Chain-of-Thoughts and Instructions for Model Reasoning, Honglin Lin*, Qizhi Pei*, Xin Gao, Zhuoshi Pan, Yu Li, Juntao Li, Conghui He, Lijun Wu†
• EMNLP 2025 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†
• ICCV 2025 Where am I? Cross-View Geo-localization with Natural Language Descriptions, Junyan Ye*, Honglin Lin*, Leyan Ou, Dairong Chen, Zihao Wang, Qi Zhu, Conghui He, Weijia Li†
• ICLR 2025 LOKI: A Comprehensive Synthetic Data Detection Benchmark using Large Multimodal Models, Junyan Ye, Baichuan Zhou, Zilong Huang, Junan Zhang, Tianyi Bai, Hengrui Kang, Jun He, Honglin Lin, Zihao Wang, Tong Wu, Zhizheng Wu, Yiping Chen, Dahua Lin, Conghui He, Weijia Li†
• ACL 2024 ContextBLIP: Doubly Contextual Alignment for Contrastive Image Retrieval from Linguistically Complex Descriptions, Honglin Lin*, Siyu Li*, Guoshun Nan†, Chaoyue Tang, Xueting Wang, Jingxin Xu, Rong Yankai, Zhouzhili Zhouzhili, Yutong Gao, Qimei Cui, Xiaofeng Tao
• Tech Report MMFineReason: Closing the Multimodal Reasoning Gap via Open Data-Centric Methods, Honglin Lin*, Zheng Liu, Yun Zhu, Chonghan Qin, Juekai Lin, Xiaoran Shang, Conghui He, Wentao Zhang, Lijun Wu†
• Tech Report Can One Domain Help Others? A Data-Centric Study on Multi-Domain Reasoning via Reinforcement Learning, Yu Li*, Zhuoshi Pan*, Honglin Lin*, Mengyuan Sun, Conghui He, Lijun Wu†
• Tech Report OpenDataArena: A Fair and Open Arena for Benchmarking Post-Training Dataset Value, Mengzhang Cai, Xin Gao, Yu Li, Honglin Lin, Zheng Liu, Zhuoshi Pan, Qizhi Pei, Xiaoran Shang, Mengyuan Sun, Zinan Tang, Xiaoyang Wang, Zhanping Zhong, Yun Zhu, Dahua Lin, Conghui He, Lijun Wu†
• Preprint Scientific Image Synthesis: Benchmarking, Methodologies, and Downstream Utility, Honglin Lin*, Chonghan Qin*, Zheng Liu, Qizhi Pei, Yu Li, Zhanping Zhong, Xin Gao, Yanfeng Wang, Conghui He, Lijun Wu†
• Preprint ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch, Zheng Liu*, Honglin Lin*, Chonghan Qin, Xiaoyang Wang, Xin Gao, Yu Li, Mengzhang Cai, Yun Zhu, Zhanping Zhong, Qizhi Pei, Zhuoshi Pan, Xiaoran Shang, Bin Cui, Conghui He, Wentao Zhang, Lijun Wu†
• Preprint SciFlow-Bench: Evaluating Structure-Aware Scientific Diagram Generation via Inverse Parsing, Tong Zhang*, Honglin Lin*, Zhou Liu, Chong Chen, Wentao Zhang†

* Equal Contribution.   † Corresponding Author

📖 Educations

• 2025.09 - Present, Ph.D. student, School of Artificial Intelligence, Shanghai Jiao Tong University (SAI, SJTU), jointly trained with Shanghai AI Laboratory.
• 2021.09 - 2025.06, B.S., School of Artificial Intelligence, Beijing University of Posts and Telecommunications (BUPT).

🎖 Honors and Awards

• 2nd place in Internal Reasoning Track of CURE-Bench@NeurIPS2025, 2025
• Outstanding Undergraduate Awards of BUPT, 2025
• Undergraduate Student National Scholarship, 2022

💻 Internships

2024.07 - Present, Shanghai Artificial Intelligent Laboratory, Shanghai, China