Yi Jiang

Yi Jiang

I am an undergraduate student at the Global Institute of Future Technology, Shanghai Jiao Tong University (class of 2024), majoring in Sustainable Energy with a minor in Artificial Intelligence.

My research sits at the intersection of machine learning and the physical sciences — AI for Science. I am particularly interested in geometric deep learning for accelerating molecular design and discovery, in building and training foundation models for science, and in self-driving laboratories and scientific agents that can close the loop between hypothesis and experiment.

I spent an exchange term at Nanyang Technological University, Singapore, where I studied data science and artificial intelligence.

Outside of work, I enjoy piano, guitar, singing, photography, and table tennis.

Feel free to reach out — I am always happy to chat! 👋

我是上海交通大学 溥渊未来技术学院 2024 级的本科生，主修可持续能源，辅修人工智能。

我的研究兴趣集中在机器学习与物质科学的交叉领域，即科学智能（AI for Science）。具体而言，我关注用几何深度学习加速分子设计与发现、科学基座大模型的开发与训练，以及能够打通“假设—实验”闭环的自驱动实验室与科学智能体。

我曾赴新加坡南洋理工大学交换学习，主修数据科学与人工智能方向课程。

工作之余，我爱好钢琴、吉他、唱歌、摄影和乒乓球。

欢迎随时联系我，我很乐意与人交流！👋

News近期动态

Sep 25, 20262026年9月25日 Awarded the National Scholarship of China.获得国家奖学金。
Sep 25, 20262026年9月25日 Our paper Matching-while-Decoding: Enhancing Template-Free Retrosynthesis via Explicit Structural Alignment was accepted to NeurIPS 2026.论文 Matching-while-Decoding: Enhancing Template-Free Retrosynthesis via Explicit Structural Alignment 被 NeurIPS 2026 接收。
Aug 22, 20262026年8月22日 My first first-author paper, PhysECD, is on arXiv — a physics-constrained E(3)-equivariant framework for predicting electronic circular dichroism spectra.首篇第一作者论文 PhysECD 上线 arXiv —— 一个用于预测电子圆二色光谱的物理约束 E(3) 等变框架。
Aug 05, 20262026年8月5日 Selected for the Bole Program at Shanghai Jiao Tong University, an honors track for the top 1% of undergraduates.入选上海交通大学伯乐计划（前 1% 本科生荣誉计划）。

Selected publications代表性工作

  1. NeurIPS
    matching-while-decoding.png
    Matching-while-Decoding: Enhancing Template-Free Retrosynthesis via Explicit Structural Alignment
    Kaipeng Zeng, Jiarui Shen, Yi Jiang, Shiyue Wang, Lin Yao, Tong Zhu, and Junchi Yan
    In Advances in Neural Information Processing Systems (NeurIPS), 2026
  2. arXiv
    physecd.png
    PhysECD: A Physics-Constrained E(3)-Equivariant Framework for Electronic Circular Dichroism Spectrum Prediction
    Yi Jiang*, Letian Chen*, Runhan Shi, Liangzhaoxuan Han, Tong Zhu, and Yang Yang
    arXiv preprint arXiv:2608.21892, Aug 2026
    arXiv