collaborators

14 papers

cs.LG2026

Active-GRPO: Adaptive Imitation and Self-Improving Reasoning for Molecular Optimization

Xuefeng Liu, Mingxuan Cao, Qinan Huang +3

Scientific reasoning is an increasingly important capability of large language models, yet improving the robustness and efficiency of training such reasoning remains a key open cha…

cs.LG2026

Active Advantage-Aligned Online Reinforcement Learning with Offline Data

Xuefeng Liu, Hung T. C. Le, Siyu Chen +4

Online reinforcement learning (RL) enhances policies through direct interactions with the environment, but faces challenges related to sample efficiency. In contrast, offline RL le…

cs.LG2026

Monte Carlo Tree Diffusion with Multiple Experts for Protein Design

Xuefeng Liu, Mingxuan Cao, Songhao Jiang +6

The goal of protein design is to generate amino acid sequences that fold into functional structures with desired properties. Prior methods combining autoregressive language models…

cs.LG2026

Multi-Objective Coverage via Constraint Active Search

Zakaria Shams Siam, Xuefeng Liu, Chong Liu

In this paper, we formulate the new multi-objective coverage (MOC) problem where our goal is to identify a small set of representative samples whose predicted outcomes broadly cove…

cs.CR2025

WGLE:Backdoor-free and Multi-bit Black-box Watermarking for Graph Neural Networks

Tingzhi Li, Xuefeng Liu, Jing Lei +1

Graph Neural Networks (GNNs) are increasingly deployed in real-world applications, making ownership verification critical to protect their intellectual property against model theft…

q-bio.QM2025

Binding Affinity Prediction: From Conventional to Machine Learning-Based Approaches

Xuefeng Liu, Songhao Jiang, Xiaotian Duan +14

Protein-ligand binding is the process by which a small molecule (drug or inhibitor) attaches to a target protein. Binding affinity, which characterizes the strength of biomolecular…