Here is Lei Liu. I am an AI researcher focused on (medical) large language models and applications. I obtained my PhD from The Chinese Univerity of Hong Kong, Shenzhen (CUHK-SZ) then joined Ant Group with the Plan A Award. Now, I am a postdoctoral researcher sponsored by Ant Group and Zhejiang University.

Hiring：The Ant-Med Algorithm Team is recruiting interns and full-time members for large-scale infra, LLM training and medical applications.

🎓 Education

🧑‍💻 Work Experience

📑 Open-spource Projects

[1] AntAngleMed

📝 Selected Publications

[1] Lei Liu, Hao Zhu, Xiaoyan Yang, Yue Shen, Zhixuan Chu, Jian Wang, Jinjie Gu, Kui Ren. Perplexity-Aware Data Scaling Law: Perplexity Landscapes Predict Performance for Continual Pre-training. Oral Presentation, ACL 2026

[2] Lei Liu, Li Liu, Yawen Cui. Prior-free Balanced Replay: Uncertainty-guided Reservoir Sampling for Long-Tailed Continual Learning. ACM-MM 2024 [HTML] [PDF]

[3] Lei Liu, Xiaoyan Yang, Fangzhou Li, Chenfei Chi, Yue Shen, Shiwei Lyu, Ming Zhang, Xiaowei Ma, Xiangguo Lyu, Liya Ma, Zhiqiang Zhang, Wei Xue, Yiran Huang, Jinjie Gu. Towards Automatic Evaluation for LLMs’ Clinical Capabilities: Metric, Data, and Algorithm. KDD 2024^▴ [HTML] [PDF]

[4] Yuxuan Zhang*, Lei Liu*, Li Liu. Cuing Without Sharing: A Federated Cued Speech Recognition Framework via Mutual Knowledge Distillation. ACM-MM 2023 [HTML] [PDF]

[5] Yaopei Zeng*, Lei Liu*, Li Liu, Li Shen, Shaoguo Liu, Baoyuan Wu. Global Balanced Experts for Federated Long-Tailed Learning. ICCV 2023 [HTML] [PDF]

[6] Lei Liu, Li Liu. Cross-modal Mutual Learning for Cued Speech Recognition. ICCV 2023 [HTML] [PDF]

[7] Lei Liu, Li Liu, Haizhou Li. Computation and Parameter Efficient Multi-Modal Fusion Transformer for Cued Speech Recognition. IEEE TASLP

[8] Xidong Wang, Shuqi Guo, Yue Shen, Junying Chen, Jian Wang, Jinjie Gu, Ping Zhang, Lei Liu^†, Benyou Wang^†. LiveClin: A Live Clinical Benchmark without Leakage

*Co-first Author ^†Corresponding Author ^▴IF at Publication
<!–

All Publications

2026

• [2026b] Chaoyang Xie, Junhu Xu, Guangyi Huang, Shihang Wang, Mutian He, Xinyu Dong, Huiyang Hong, Xiaojun Yao, Qi Wang*, Yuquan Li*. Spectral decomposition of chemical semantics for activity cliffs-aware molecular property prediction[J]. Advanced Science, 2026: e17579. [HTML] [PDF]
• [2026a] Huiyang Hong, Xinkai Wu, Hongyu Sun, Chaoyang Xie, Qi Wang*, Yuquan Li*. Learning hierarchical interaction for accurate molecular property prediction[J]. Communications Chemistry,2026. [HTML] [PDF]
• [2026c] Chaoyang Xie, Xiaorui Wang, Yawen Dong, Xiaojun Yao*, Gefei Hao*, Yuquan Li*. Reshaping the drug discovery ecosystem with open science and collaborative innovation[J]. The Innovation Drug Discovery, 2026, 1(1): 100016. [HTML] [PDF]

2025

• [2025c] Yanan Tian, Ruiqiang Lu, Xiaoqing Gong, Yuquan Li, Wei Zhao, Xiaorui, Wang, Xinming Jia, Qin Li, Yuwei Yang, Henry H. Y. Tong, Joel P. Arrais*, Huanxiang Liu*, Xiaojun Yao*. Enhancing Kinase-Inhibitor Activity and Selectivity Prediction Through Multimodal and Multiscale Contrastive Learning with Attention Consistency[J]. Nature Communications,2025,16:10860. [HTML] [PDF]
• [2025b] Xiaorui Wang†, Xiaodan Yin†, Xujun Zhang†, Huifeng Zhao, Shukai Gu, Zhenxing Wu, Odin Zhang, Wenjia Qian, Yuansheng Huang, Yuquan Li, Dejun Jiang, Mingyang Wang, Huanxiang Liu, Xiaojun Yao*, Chang-Yu Hsieh*, Tingjun Hou*. A virtual platform for automated hybrid organic-enzymatic synthesis planning[J]. Nature Communications,2025,16:10929. [HTML] [PDF]
• [2025a] Zhenglu Chen, Chunbin Gu*, Shuoyan Tan, Xiaorui Wang, Yuquan Li, Mutian He, Ruiqiang Lu, Shijia Sun, Chang-Yu Hsieh*, Xiaojun Yao*, Huanxiang Liu*, Pheng-Ann Heng. Interpretable PROTAC Degradation Prediction With Structure-Informed Deep Ternary Attention Framework[J]. Advanced Science, 2025. [HTML] [PDF]

2024

• [2024a] Xiaorui Wang, Xiaodan Yin, Dejun Jiang, Huifeng Zhao, Zhenxing Wu, Odin Zhang, Jike Wang, Yuquan Li, Yafeng Deng, Huanxiang Liu, Pei Luo, Yuqiang Han, Tingjun Hou*, Xiaojun Yao*, Chang-Yu Hsieh*. Multi-modal deep learning enables efficient and accurate annotation of enzymatic active sites[J]. Nature Communications, 2024, 15(1): 7348. [HTML] [PDF]

2023

• [2023a] Xiaorui Wang†, Chang-Yu Hsieh†, Xiaodan Yin, Jike Wang, Yuquan Li, Yafeng Deng, Dejun Jiang, Zhenxing Wu, Hongyan Du, Hongming Chen, Yun Li, Huanxiang Liu, Yuwei Wang, Pei Luo, Tingjun Hou*, Xiaojun Yao*. Generic Interpretable Reaction Condition Predictions with Open Reaction Condition Datasets and Unsupervised Learning of Reaction Center[J]. Research, 2023, 6: 0231. [HTML] [PDF]

2022

• [2022a] Yuquan Li†, Chang-Yu Hsieh†, Ruiqiang Lu, Xiaoqing Gong, Xiaorui Wang, Pengyong Li, Shuo Liu, Yanan Tian, Dejun Jiang, Jiaxian Yan, Qifeng Bai, Huanxiang Liu, Shengyu Zhang , Xiaojun Yao*. An adaptive graph learning method for automated molecular interactions and properties predictions[J]. Nature Machine Intelligence, 2022, 4(7):645-651. [HTML] [PDF]

2021

• [2021c] Pengyong Li†, Yuquan Li†, Chang-Yu Hsieh, Shengyu Zhang, Xianggen Liu, Huanxiang Liu, Sen Song*, Xiaojun Yao*. TrimNet: learning molecular representation from triplet messages for biomedicine[J]. Briefings in Bioinformatics, 2021, 22(4): bbaa266.[HTML] [PDF]
• [2021b] Xiaorui Wang†, Yuquan Li†, Jiezhong Qiu, Guangyong Chen, Huanxiang Liu, Benben Liao*, Chang-Yu Hsieh*, Xiaojun Yao*. RetroPrime: A Diverse, plausible and Transformer-based method for Single-Step retrosynthesis predictions[J]. Chemical Engineering Journal, 2021, 420: 129845. [HTML] [PDF]
• [2021a] Yuquan Li, Pengyong Li, Xing Yang, Chang-Yu Hsieh, Shengyu Zhang, Xiaorui Wang, Ruiqiang Lu, Huanxiang Liu, Xiaojun Yao*. Introducing block design in graph neural networks for molecular properties prediction[J]. Chemical Engineering Journal, 2021, 414: 128817. [HTML] [PDF]
  –>