Yicong Li
Little Havana, 2025
I’m a Ph.D. candidate in Computer Science at Harvard University, advised by Prof. Hanspeter Pfister in Visual Computing Group (VCG), with an M.S. in Bioengineering. I also work with Prof. Jeff W. Lichtman, Prof. Aravinthan D.T. Samuel, Prof. Dmitri “Mitya” B. Chklovskii, Prof. Jingpeng Wu, Prof. Bill Lotter, and Prof. Wanhua Li.
Previously, I obtained my master’s degree from Tsinghua University advised by Prof. Yang Li and my bachelor’s degree from Sichuan University’s Wu Yuzhang Honors College. During this period, I was fortunate to work with Prof. Nir Shavit and Prof. Lu Mi at MIT CSAIL, and Prof. Faisal Mahmood at Harvard Medical School.
I interned at Netflix, Genentech, Microsoft Research (with Dr. Kristen Severson), Simons Foundation’s Flatiron Institute, and Huawei (with Prof. Nanshan Zhong’s team).
I aim to develop bleeding-edge AI techniques to address important real-world challenges. My recent work explores:
- Vision-Language Model Post-Training: supervised fine-tuning, reinforcement learning, in-context learning, and synthetic data generation.
- Self-Evolving Agentic Systems: automatic prompt/skill/workflow/harness optimization.
- Computer Vision: 2D & 3D image segmentation/restoration/compression, object detection, self-supervised learning, and vision foundation models.
- Generative Models: VAEs, GANs, and diffusion models.
- AI for Neuroscience: large-scale electron microscopy image analysis for connectomics.
- AI for Healthcare: computational pathology, respiratory disease screening and quality assurance, embryo viability prediction in IVF, and MRI/CT/X-ray image analysis.
I’m a recipient of the Laverack Family Innovation Fund Fellowship in the Division of Engineering and Applied Sciences from Harvard University and the prestigious (only 5) “Wang Wen Guo” scholarship from Sichuan University. My research has been featured in MIT News, Forbes, MarkTechPost, Computer Vision News, and ERCIM News.
I'm currently on the industry job market — feel free to reach out!
Selected Publications
- Deep learning for spirometry quality assurance with spirometric indices and curvesRespiratory Research, 2022
- How Does Policy Stringency Affect the Spread of COVID-19 Pandemic? A Country Level StudyIn 29th European Signal Processing Conference (EUSIPCO), 2021Oral
- SmartEM: Machine-Learning Guided Electron Microscopy2025Nature Methods
- WASPSYN: A Challenge for Domain Adaptive Synapse Detection in Microwasp Brain ConnectomesIEEE Transactions on Medical Imaging, 2024
- Correcting Non-Uniform Milling in FIB-SEM Images with Unsupervised Cross-Plane Image-to-Image TranslationbioRxiv, 2025
- Joint PVL Detection and Manual Ability Classification Using Semi-Supervised Multi-Task LearningIn International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2021
- Efficient Prediction of Model Transferability in Semantic Segmentation TasksIn 2023 IEEE International Conference on Image Processing (ICIP), 2023
- Investigating Consistency Constraints in Heterogeneous Multi-Task Learning for Medical Image ProcessingIn 2023 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) Workshop, 2023
- MoRA: LoRA Guided Multi-Modal Disease Diagnosis with Missing ModalityIn International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2024Early Acceptance
- Multimodal Learning for Embryo Viability Prediction in Clinical IVFIn International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2024
- Towards 1000-Fold Electron Microscopy Image Compression for Connectomics via VQ-VAE with Transformer PriorIn IEEE 23rd International Symposium on Biomedical Imaging (ISBI), 2026
- LiDAR Integrated IR OWC System with Abilities of User Localization and High-Speed Data TransmissionOptics Express, 2022