Arash

Arash

he/him

MSc Computer Science student researching machine learning, LLMs, and AI fairness. Research Assistant at the Vector Institute.

From Bias to Breakdown: Benchmarking Failure Mode Analysis of Single-cell RNA Sequencing Foundation Models in Acute Myeloid Leukemia

Published in Proceedings of the AAAI Symposium Series, 2025

This study provides a comprehensive benchmarking of failure modes in foundation models applied to single-cell RNA sequencing data for Acute Myeloid Leukemia. It systematically explores algorithmic biases and model breakdowns to better understand the limitations of these models in critical bioinformatics applications.

Recommended citation: Naziri, A., Asgari, A., An, A., Sachlos, E., & Seyyed-Kalantari, L. (2025). "From Bias to Breakdown: Benchmarking Failure Mode Analysis of Single-cell RNA Sequencing Foundation Models in Acute Myeloid Leukemia." Proceedings of the AAAI Symposium Series, 7(1), 553-557.
Download Paper