Zexuan Zhu

NanoSimFormer generates high-fidelity nanopore sequencing signals optimized for accurate basecalling, outperforming existing simulators across multiple datasets and tasks.

Polus improves DNA storage reliability and efficiency by using a Transformer-based platform to reduce sequencing coverage and errors.

The paper introduces a dual-LLM adversarial framework to improve information extraction from scientific texts, showing better performance than single-LLM and manual methods.

PepCCD generates target-specific peptides using a contrastive conditioned diffusion framework, achieving strong binding affinity and improved diversity compared to existing methods.

The paper introduces MCGLPPI, a geometric representation learning framework that combines graph neural networks with a molecular coarse-grained model to predict PPI properties efficiently.

The paper introduces an active module identification algorithm for PPI networks using a convex optimization approach, showing effectiveness on single and multilayer networks.