Rong-Xi Tan

Rong-Xi Tan

Nanjing University

Hi, this is Rong-Xi Tan. Currently I am a first-year PhD student of School of Artificial Intelligence in Nanjing University advised by Prof. Chao Qian and a member of LAMDA Group, led by Prof. Zhi-Hua Zhou.

My research interest lies in Text-to-text regression and black-box optimization (BBO) algorithms, and their applications in AI4Science (e.g., geoscience and soil property analysis) and industrial scenarios (e.g., electronic design automation).

🔥 News

  • 2025.05:  🎉🎉 UniSO is accepted by ICML’25.
  • 2025.01:  🎉🎉 Offline-RaM is accepted by ICLR’25.
  • 2024.12:  🎉🎉 I obtained Top-Grade Scholarship of Nanjing University.
  • 2024.09:  🎉🎉 I obtained National Science Foundation for Undergraduates.
  • 2024.05:  🎉🎉 Offline-MOO is accepted by ICML’2024.
  • 2024.04:  🎉🎉 I was awarded as a Merit Student of Jiangsu Province.
  • 2024.04:  🎉🎉 Hi, I finally create my personal page.

📝 Publications

📤 Preprint

  1. Ming Chen*, Sheng Tang*, Rong-Xi Tan*, Ziniu Li, Jiacheng Chen, Ke Xue, Chao Qian. Beyond Token-level Supervision: Unlocking the Potential of Decoding-based Regression via Reinforcement Learning. arXiv:2512.06533. [Paper]
  2. Ke Xue*, Ruo-Tong Chen*, Rong-Xi Tan*, Xi Lin, Yunqi Shi, Siyuan Xu, Mingxuan Yuan, Chao Qian. BBOPlace-Bench: Benchmarking Black-Box Optimization for Chip Placement. arXiv:2510.23472. [Paper] [Code]

📈 Conference

  1. Rong-Xi Tan*, Ming Chen*, Ke Xue, Yao Wang, Yaoyuan Wang, Sheng Fu, Chao Qian. Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings. In: Proceedings of the 42nd International Conference on Machine Learning (ICML’25), Vancouver, Canada, 2025, to appear. [Paper] [Code]
    Also in: 2nd Workshop on Foundation Models in the Wild at ICLR’25, Singapore, 2025. (Oral presentation)
  2. Rong-Xi Tan, Ke Xue, Shen-Huan Lyu, Haopu Shang, Yao Wang, Yaoyuan Wang, Sheng Fu, Chao Qian. Offline Model-Based Optimization by Learning to Rank. In: Proceedings of the 13th International Conference on Learning Representation (ICLR’25), Singapore, 2025. [Paper] [Code]
  3. Ke Xue*, Rong-Xi Tan*, Xiaobin Huang, Chao Qian. Offline Multi-Objective Optimization. In: Proceedings of the 41st International Conference on Machine Learning (ICML’24), Vienna, Austria, 2024, pp. 55595-55624. [Paper] [Code]

📚 Journal

  1. Han Hu*, Chao Qian*, Ke Xue*, Rainer Georg Jörgensen, Marco Keiluweit, Chao Liang, Xuefeng Zhu, Ji Chen, Yishen Sun, Haowei Ni, Jixian Ding, Weigen Huang, Jingdong Mao, Rong-Xi Tan, Jizhong Zhou, Thomas W. Crowther, Zhi-Hua Zhou, Jiabao Zhang, and Yuting Liang. Reducing the Uncertainty in Estimating Soil Microbial Derived Carbon Storage. Proceedings of the National Academy of Sciences (PNAS), 2024, 121(35): e2401916121. [Paper]

🎖 Honors and Awards

  • 2025.06: Research results reported by NSFC [Link].
  • 2024.12: Nanjing University Top-Grade Scholarship (the highest honor at Nanjing University).
  • 2024.09: National Science Foundation for Undergraduates (国家自然科学基金本科生项目).
  • 2024.04: Merit Student of Jiangsu Province.
  • 2023.11: Bailu Scholarship, Nanjing University.
  • 2023.07: Pacemaker to Outstanding students, Nanjing University.
  • 2023.05: One Hundred Outstanding Youths of Qixia District, Communist Youth League of Qixia District.
  • 2022.11: Second Prize Nationwide in National University Mathematical Modeling Competition (MCM).

📪 Services

Conference Reviewer:

  • ICLR: 2025, 2026
  • NeurIPS: 2025

📖 Educations

💬 Invited Talks

  • 2025.09, Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings. @ LEAD Workshop by SCUT, Virtual.

🥳 Miscellaneous

  • My Chinese name is 谭荣熙 (Tan Rongxi), which can be pronounced as /tɑːm wɪŋ ‘heɪ/ in Cantonese.
  • I sincerely enjoy in Cantopop, and I am a fan of Joey. It would be absolutely cool if you are also interested in 心之科學.
  • I also enjoy working out, like going to the gym💪, jogging🏃, and playing badminton🏸 (though I could not play it for a long time due to injury😭).