papers

Publications (7)

cs.LG2025

On the Hardness of Sampling from Mixture Distributions via Langevin Dynamics

Xiwei Cheng, Kexin Fu, Farzan Farnia

The Langevin Dynamics (LD), which aims to sample from a probability distribution using its score function, has been widely used for analyzing and developing score-based generative…

math.OC2021

Non-Convex Joint Community Detection and Group Synchronization via Generalized Power Method

Sijin Chen, Xiwei Cheng, Anthony Man-Cho So

This paper proposes a Generalized Power Method (GPM) to tackle the problem of community detection and group synchronization simultaneously in a direct non-convex manner. Under the…

cs.LG2026

DrugSAGE:Self-evolving Agent Experience for Efficient State-of-the-Art Drug Discovery

Yikun Zhang, Xiwei Cheng, Tianyu Liu +2

Building state-of-the-art (SOTA) predictive models for drug discovery requires expensive search over tools, architectures, and training strategies. Current LLM-based agents can fin…

q-bio.BM2024

DecompOpt: Controllable and Decomposed Diffusion Models for Structure-based Molecular Optimization

Xiangxin Zhou, Xiwei Cheng, Yuwei Yang +3

Recently, 3D generative models have shown promising performances in structure-based drug design by learning to generate ligands given target binding sites. However, only modeling t…

cs.IT2022

Generalized Group Testing

Xiwei Cheng, Sidharth Jaggi, Qiaoqiao Zhou

In the problem of classical group testing one aims to identify a small subset (of size ) diseased individuals/defective items in a large population (of size ). This process i…

cs.LG2025

Stability and Generalization in Free Adversarial Training

Xiwei Cheng, Kexin Fu, Farzan Farnia

While adversarial training methods have significantly improved the robustness of deep neural networks against norm-bounded adversarial perturbations, the generalization gap between…

q-bio.BM2026

Decomposed Direct Preference Optimization for Structure-Based Drug Design

Xiwei Cheng, Xiangxin Zhou, Yuwei Yang +2

Diffusion models have achieved promising results for Structure-Based Drug Design (SBDD). Nevertheless, high-quality protein subpocket and ligand data are relatively scarce, which h…