Yunlin Fu

The paper benchmarks 13 models for predicting single-cell perturbation responses across 25 datasets, finding performance varies with perturbation effect size and evaluation metric.

The paper introduces a framework for self-auditing AI in drug discovery, using verifiers to validate predictions and adjust objectives based on experimental results.

The paper develops DynaALS, a disease dynamics atlas for ALS that maps patient states and molecular programs using longitudinal medical records and multi-omics data.

RVQ-Alpha adapts large language models for single-cell analysis by integrating hierarchical tokenization and reinforcement learning, achieving performance comparable to task-specific models on a multi-task benchmark.