3 papers
cs.LG2025
Interpretable Perturbation Modeling Through Biomedical Knowledge Graphs
Pascal Passigan, Kevin Zhu, Angelina Ning
Understanding how small molecules perturb gene expression is essential for uncovering drug mechanisms, predicting off-target effects, and identifying repurposing opportunities. Whi…
eess.IV2024
Analyzing the Effect of -Space Features in MRI Classification Models
Pascal Passigan, Vayd Ramkumar
The integration of Artificial Intelligence (AI) in medical diagnostics is often hindered by model opacity, where high-accuracy systems function as "black boxes" without transparent…
cs.CL2023
Continuous Prompt Generation from Linear Combination of Discrete Prompt Embeddings
Pascal Passigan, Kidus Yohannes, Joshua Pereira
The wayward quality of continuous prompts stresses the importance of their interpretability as unexpected and unpredictable behaviors appear following training, especially in the c…