Rate My Professor Donglai Wei

Donglai Wei is an Assistant Professor of Computer Science at Boston College, where he directs the Machine Learning for Science Lab. His research explores the interplay between biological sciences and computer vision, with a focus on building computational models for biomedical image analysis, including connectomics, and applying brain mechanisms to enhance machine video understanding. Wei received a B.S. in Mathematics from Brown University after transferring from Tsinghua University and earned his Ph.D. from the Massachusetts Institute of Technology's Computer Science and Artificial Intelligence Laboratory, advised by William T. Freeman. Before joining Boston College in 2021, he served as a postdoctoral fellow in Harvard University's Visual Computing Group within the John A. Paulson School of Engineering and Applied Sciences.

Wei's scholarly contributions include high-impact datasets such as the MitoEM Dataset for large-scale 3D mitochondria instance segmentation from electron microscopy images (MICCAI 2020), AxonEM Dataset for 3D axon instance segmentation (MICCAI 2021), NucMM Dataset for 3D neuronal nuclei instance segmentation (MICCAI 2021), and RibSeg for rib segmentation from CT scans (MICCAI 2021). His publications feature prominently in leading venues, including 'A Connectomic Study of a Petascale Fragment of Human Cerebral Cortex' (Science, 2024, co-authored with colleagues), 'Dense 4D Nanoscale Reconstruction of Living Brain Tissue' (Nature Methods, 2023), 'Multiplexed Volumetric CLEM Enabled by ScFvs Provides Insights into the Cytology of Cerebellar Cortex' (Nature Communications, 2024), 'Video Enhancement with Task-Oriented Flow' (IJCV, 2019), 'Learning and Using the Arrow of Time' (CVPR, 2018), and 'Microscope for Visualizing and Quantifying Small Motions' (PNAS, 2017). He has received a $600,000 NSF CAREER Award to advance human-centric machine learning, a grant from Boston College's Schiller Institute, and a Student Travel Award at MICCAI 2021. Wei collaborates on interdisciplinary projects, including neuroscience publications and engineering initiatives, contributing tools like VesiclePy, BiaPy, and SynAnno for electron microscopy analysis.