上一篇 冯杰
付靖文 下一篇
冯世坤
北京中关村学院导师
冯世坤，博士毕业于清华大学计算机系，研究方向聚焦于表示学习与 AI4Science。以第一作者身份在 ICLR、ICML、NeurIPS、Nature Machine Intelligence 等国际会议与期刊上发表多篇论文，并长期担任 ICLR、ICML、NeurIPS 等会议审稿人。曾获清华大学慧妍奖学金，入选清华大学计算机系优秀毕业生。研究方向围绕Science领域的表示学习展开，重点探索基础模型的预训练策略、多模态融合，以及生成与理解任务的统一框架等方向。
个人主页：https://fengshikun.github.io/
个人主页：https://fengshikun.github.io/
人物经历
研究方向
1. 自监督学习
2. 多模态融合
3. AI4Science
4. 计算机视觉
代表性学术论文
1. Shikun Feng, Yuyan Ni, Minghao Li, Yanwen Huang, Zhi-Ming Ma, Wei-Ying Ma, Yanyan Lan. UniCorn: A Unified Contrastive Learning Approach for Multi-view Molecular Representation Learning. International Conference on Machine Learning (ICML 2024)
2. Shikun Feng, Yuyan Ni, Yanyan Lan, Zhi-Ming Ma, Wei-Ying Ma. Fractional Denoising for 3D Molecular Pre-training. International Conference on Machine Learning (ICML 2023)
3. Shikun Feng, Yuyan Ni, Yan Lu, Zhi-Ming Ma, Wei-Ying Ma, Yanyan Lan. UniGEM: A Unified Approach to Generation and Property Prediction for Molecules. International Conference on Learning Representations (ICLR 2025)
4. Shikun Feng, Minghao Li, Yinjun Jia, Wei-Ying Ma, Yanyan Lan. Protein-Ligand Binding Representation Learning from Fine-Grained Interactions. International Conference on Learning Representations (ICLR 2024)
5. Shikun Feng, Bicheng Lin, Yuanhuan Mo, Yuyan Ni, Wenyu Zhu, Bowen Gao, Wei-Ying Ma, Yanyan Lan. FIGRDock: Fast Interaction-Guided Regression for Flexible Docking (NeurIPS 2025)
6. Yuyan Ni, Shikun Feng, Xin Hong, Yuancheng Sun, Wei-Ying Ma, Zhi-Ming Ma, Qiwei Ye. Pre-training with Fractional Denoising to Enhance Molecular Property Prediction. Nature Machine Intelligence (2024)
7. Yuyan Ni, Shikun Feng, Haohan Chi, Bowen Zheng, Huan-ang Gao, Wei-Ying Ma, Zhi-Ming Ma, Yanyan Lan. Straight-Line Diffusion Model for Efficient 3D Molecular Generation(NeurIPS 2025)
主要成就与荣誉
清华大学计算机系优秀毕业生
清华大学慧妍人才奖学金