Xuanbai Ren
I am a Ph.D. candidate at the school of computer science, Hunan University, under the supervision of Prof.Xiangxiang Zeng and Prof.Yiping Liu. Previously, I obtained my M.E. degree at the school of computer science, Hunan University in 2022, working with Prof.Lijun Cai and Prof.Xiangzheng Fu. I earned my B.E. degree from Hengyang Normal University in 2019.
Research Interest: My research interests cover many aspects of machine learning and its applications in drug discovery.
- Machine Learning: 1) Language Model, its applications in drug property design ; 2) Multi-objective optimization algorithm, with applications in drug design conflict tasks.
Publication & Activities: Most of my research papers have been published in interdisciplinary journals and computer science conferences, such as Nature Communications, Advanced Science, Bioinformatics, ACL, AAAI, NeurIPS, and CVPR. A full publication list can be found at google scholar. I also serve as reviewer in
- Conferences: ICLR (2024-2025), ICLR (2025-2026), NeurIPS (2025-2026), AAAI (2026-2027)
- Journals: Bioinformatics, Briefings in Bioinformatics, Scientific Reports, JCIM.
More Things: N/A.
news
| Apr 7, 2026 | 🎉 Our work CAML (A Conflict-Aware Molecular Language Model Merging Framework for Multi-Constraint Molecular Generation) is accepted to ACL 2026 main conference! 🧬🤖. We introduce a novel game-theoretic framework that uses SACMA-ES to find the Nash Equilibrium among expert models, resolving property conflicts efficiently without re-training. |
|---|---|
| Apr 1, 2026 | 🎉 Our latest multidisciplinary work, “AI Identifies Compounds that Protect Retinal Ganglion Cells and Optic Nerve in Neurodegeneration by Alleviating ER Stress,” is currently under review at Nature Communications. In this study, we developed an AI-driven pipeline utilizing ImageMol, a visually pre-trained molecular representation model, to discover neuroprotective agents targeting ER stress for glaucoma. By virtually screening over 10,000 clinically tested compounds, we successfully identified and experimentally validated two candidates (leonurine hydrochloride and chlorogenic acid) that preserve retinal ganglion cell (RGC) viability and improve visual function in vivo. This provides a scalable, mechanism-specific framework for drug discovery in neurodegenerative diseases. |
| Mar 1, 2026 | 🚀 MolDeriveX is officially open-sourced! Our core methodology paper, “Multi-objective generative algorithm enables broad-spectrum antibiotic derivatization”. We are thrilled to release the complete codebase of our synergistic local-global generative framework, empowering the community to combat the escalating AMR crisis. 🔥 Highlighted Updates in this Release:
|
| Feb 21, 2026 | 🎉 Our work STEPH (Sparse Task Vector Mixup with Hypernetworks for Efficient Knowledge Transfer in Whole-Slide Image Prognosis) is accepted to CVPR 2026. As a continuation of CROPKT, this work presents an efficient solution: prognosis knowledge transfer via model merging. Paper and codes will be released soon. Stay tuned. |
| Dec 7, 2025 | 🎉 Our paper “Self-supervised Blending for Molecular Sequence Generation” was accepted by NeurIPS 2025! We introduce a blending-based SSL strategy to surmount the data scarcity challenge in molecular design. |
| Feb 25, 2025 | 🎉 Our paper “Multi-Objective Molecular Design Through Learning Latent Pareto Set” was accepted by AAAI 2025! We propose a novel framework to approximate the entire Pareto set, empowering researchers to fine-tune molecular properties with ease. 🧪✨ Code |
| Aug 30, 2024 | 🎉 Our paper “DeepAMP A Foundation Model Identifies Broad-Spectrum Antimicrobial Peptides against Drug-Resistant Bacterial Infection” is published in Nature Communications! In this study, we developed deepAMP, a peptide language-based deep generative framework designed to expedite the discovery of potent, broad-spectrum antimicrobial peptides (AMPs). By employing a novel sequence degradation strategy and multi-stage fine-tuning, we identified 29 high-potential candidates. These peptides proved effective in treating P. aeruginosa skin wound infections in mouse models with excellent biocompatibility. |
| May 5, 2024 | 🎉 Our work HydrogelFinder (A Foundation Model for Efficient Self-Assembling Peptide Discovery Guided by Non-Peptidal Small Molecules) is accepted to Advanced Science. By leveraging non-peptidal small molecules to guide chemical space exploration, we’ve achieved a rapid 19-day workflow from generation to wet-lab validation. 🧪 Our model successfully identified 9 novel self-assembling peptides (1-10 amino acids), including the shortest lipid-peptide documented to date. |
