collaborators

5 papers

q-bio.BM2026

SF-Cluster: Frustration-Guided MSA Subsampling for Alternative Protein Conformation Recovery

Hanqun Cao, Zijun Gao, Chunbin Gu +3

Deep-learning structure predictors are sensitive to their multiple sequence alignment (MSA) input, making MSA subsampling a practical route to recovering alternative conformations.…

cs.LG2026

Generative Modeling of Discrete Latent Structures via Dynamic Policy Gradients

Stefan Ivanovic, Ge Liu, Mohammed El-Kebir

Many scientific problems require inferring unobserved mechanistic latent states from indirect observations. While classical approaches, including expectation maximization, do not s…

cs.LG2026

Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewards

Fang Wu, Aaron Tu, Weihao Xuan +21

Reinforcement learning with verifiable rewards (RLVR) is a practical, scalable way to improve large language models on math, code, and other structured tasks. However, we argue tha…

cs.LG2025

From Supervision to Exploration: What Does Protein Language Model Learn During Reinforcement Learning?

Hanqun Cao, Hongrui Zhang, Junde Xu +12

Protein language models (PLMs) have advanced computational protein science through large-scale pretraining and scalable architectures. In parallel, reinforcement learning (RL) has…

cs.LG2025

Lightweight MSA Design Advances Protein Folding From Evolutionary Embeddings

Hanqun Cao, Xinyi Zhou, Zijun Gao +7

Protein structure prediction often hinges on multiple sequence alignments (MSAs), which underperform on low-homology and orphan proteins. We introduce PLAME, a lightweight MSA desi…