Vision-Language Modeling for Neuropathological Evaluation
About
Recent development in vision-language models has enabled flexible multimodal understanding and instruction-following. In this work, we introduce a vision-language framework for neuropathology that emphasizes diagnostic accuracy through visual QA. Without dense spatial supervision, this framework achieves accurate and reliable diagnostic decision making for a wide array of comorbid neuropathologies, offering a disease-agnostic approach for neuropathological evaluation.
Speaker
Lingyi Xu
Lingyi Xu is a Ph.D. student in the Faculty of Computing & Data Sciences at Boston University. She works with Professor Vijaya B. Kolachalama to seek solutions to data missingness in multimodal learning. Her work investigates how different data modalities can be represented and aligned to make learning more adaptable and their relationships more interpretable.