Assistant Professor, Boston University, Boston University
2 papers at NeurIPS 2025
JADE is a unified framework that simultaneously learns spot-wise alignments and shared low-dimensional embeddings to robustly integrate multi-slice spatial transcriptomics data.
We propose GTrans, a transfer learning framework that enhances graphon estimation for small graphs via neighborhood smoothing, Gromov-Wasserstein transport, and adaptive debiasing, boosting link prediction and graph classification.
