publications

2026

1. Thesis

   Leveraging Active Reinforcement Learning and Generative Models for Biomolecular Design

   Xuefeng Liu

   University of Chicago, 2026

   Bib

   @article{liu2026leveraging,
     title = {Leveraging Active Reinforcement Learning and Generative Models for Biomolecular Design},
     author = {Liu, Xuefeng},
     journal = {University of Chicago},
     year = {2026},
     publisher = {University of Chicago}
   }

2. Preprint

   Regime-Adaptive Bayesian Optimization via Dirichlet Process Mixtures of Gaussian Processes

   Yan Zhang, Xuefeng Liu, Sipeng Chen, and 3 more authors

   arXiv preprint arXiv:2601.20043, 2026
3. JCIM

   CACHE Challenge# 3: Targeting the Nsp3 Macrodomain of SARS-CoV-2

   Oleksandra Herasymenko, Madhushika Silva, Galen J Correy, and 8 more authors

   Journal of Chemical Information and Modeling, 2026

   Bib

   @article{herasymenko2026cache,
     title = {CACHE Challenge\# 3: Targeting the Nsp3 Macrodomain of SARS-CoV-2},
     author = {Herasymenko, Oleksandra and Silva, Madhushika and Correy, Galen J and Abu-Saleh, Abd Al-Aziz A and Ackloo, Suzanne and Arrowsmith, Cheryl and Ashworth, Alan and Ban, Fuqiang and Beck, Hartmut and Bishop, Kevin P and others},
     journal = {Journal of Chemical Information and Modeling},
     year = {2026},
     publisher = {ACS Publications}
   }

4. AAMAS

   Multi-Objective Coverage via Constraint Active Search

   Zakaria Siam, Xuefeng Liu, and Chong Liu

   International Conference on Autonomous Agents and Multiagent Systems, 2026

   Oral Presentation

   Oral

2025

1. MLHC

   Bidirectional Hierarchical Protein Multi-Modal Representation Learning

   Xuefeng Liu, Songhao Jiang, Chih-chan Tien, and 2 more authors

   Machine Learning for Healthcare, 2025

   Bib

   @article{liu2025bidirectional,
     title = {Bidirectional Hierarchical Protein Multi-Modal Representation Learning},
     author = {Liu, Xuefeng and Jiang, Songhao and Tien, Chih-chan and Xu, Jinbo and Stevens, Rick},
     journal = {Machine Learning for Healthcare},
     year = {2025}
   }

2. Preprint

   DrugImproverGPT: A Large Language Model for Drug Optimization with Fine-Tuning via Structured Policy Optimization

   Xuefeng Liu, Songhao Jiang, Siyu Chen, and 4 more authors

   arXiv preprint arXiv:2502.07237, 2025

   Bib

   @article{liu2025drugimprovergpt,
     title = {DrugImproverGPT: A Large Language Model for Drug Optimization with Fine-Tuning via Structured Policy Optimization},
     author = {Liu, Xuefeng and Jiang, Songhao and Chen, Siyu and Yang, Zhuoran and Chen, Yuxin and Foster, Ian and Stevens, Rick},
     journal = {arXiv preprint arXiv:2502.07237},
     year = {2025}
   }

3. ICML-GenBio

   A ground-up designed controllable gpt for molecule optimization

   Xuefeng Liu, Songhao Jiang, Bo Li, and 1 more author

   In ICML 2025 Generative AI and Biology (GenBio) Workshop, 2025

   Bib

   @inproceedings{liu2025ground,
     title = {A ground-up designed controllable gpt for molecule optimization},
     author = {Liu, Xuefeng and Jiang, Songhao and Li, Bo and Stevens, Rick L},
     booktitle = {ICML 2025 Generative AI and Biology (GenBio) Workshop},
     year = {2025}
   }

4. ICML-GenBio

   Scaffold-driven gpt model for drug optimization

   Xuefeng Liu, Songhao Jiang, Ian Foster, and 2 more authors

   In ICML 2025 Generative AI and Biology (GenBio) Workshop, 2025

   Bib

   @inproceedings{liu2025scaffold,
     title = {Scaffold-driven gpt model for drug optimization},
     author = {Liu, Xuefeng and Jiang, Songhao and Foster, Ian and Xu, Jinbo and Stevens, Rick L},
     booktitle = {ICML 2025 Generative AI and Biology (GenBio) Workshop},
     year = {2025}
   }

5. ICML-EXAIT

   Active Advantage-Aligned Online Reinforcement Learning with Offline Data

   Xuefeng Liu, Hung TC Le, Siyu Chen, and 4 more authors

   In ICML 2025 The Exploration in AI Today Workshop, 2025

   Bib

   @inproceedings{liu2025active,
     title = {Active Advantage-Aligned Online Reinforcement Learning with Offline Data},
     author = {Liu, Xuefeng and Le, Hung TC and Chen, Siyu and Stevens, Rick and Yang, Zhuoran and Walter, Matthew and Chen, Yuxin},
     booktitle = {ICML 2025 The Exploration in AI Today Workshop},
     year = {2025}
   }

6. MLHC

   ScaffoldGPT: A Scaffold-based GPT Model for Drug Optimization

   Xuefeng Liu, Songhao Jiang, Ian Foster, and 2 more authors

   Machine Learning for Healthcare, 2025

   Bib

   @article{liu2025scaffoldgpt,
     title = {ScaffoldGPT: A Scaffold-based GPT Model for Drug Optimization},
     author = {Liu, Xuefeng and Jiang, Songhao and Foster, Ian and Xu, Jinbo and Stevens, Rick},
     journal = {Machine Learning for Healthcare},
     year = {2025}
   }

7. NeurIPS-AI4D3

   Monte Carlo Tree Diffusion with Multiple Experts for Protein Design

   Xuefeng Liu, Mingxuan Cao, Songhao Jiang, and 6 more authors

   NeurIPS 2025 Workshop on AI Virtual Cells and Instruments, 2025

   Bib

   @article{liu2025monte,
     title = {Monte Carlo Tree Diffusion with Multiple Experts for Protein Design},
     author = {Liu, Xuefeng and Cao, Mingxuan and Jiang, Songhao and Luo, Xiao and Duan, Xiaotian and Wang, Mengdi and Sosnick, Tobin R and Xu, Jinbo and Stevens, Rick},
     journal = {NeurIPS 2025 Workshop on AI Virtual Cells and Instruments},
     year = {2025}
   }

8. NeurIPS-AI4D3

   FragmentGPT: A Unified GPT Model for Fragment Growing, Linking, and Merging in Molecular Design

   Xuefeng Liu, Songhao Jiang, Qinan Huang, and 5 more authors

   NeurIPS 2025 Workshop on AI Virtual Cells and Instruments, 2025

   Oral at NeurIPS-AI4D3 2025 Bib

   Oral

   @article{liu2025fragmentgpt,
     title = {FragmentGPT: A Unified GPT Model for Fragment Growing, Linking, and Merging in Molecular Design},
     author = {Liu, Xuefeng and Jiang, Songhao and Huang, Qinan and Xu, Tinson and Foster, Ian and Wang, Mengdi and Lin, Hening and Stevens, Rick},
     journal = {NeurIPS 2025 Workshop on AI Virtual Cells and Instruments},
     year = {2025},
   }

9. Preprint

   ControllableGPT: A Ground-Up Designed Controllable GPT for Molecule Optimization

   Xuefeng Liu, Songhao Jiang, Bo Li, and 1 more author

   arXiv preprint arXiv:2502.10631, 2025

   Bib

   @article{liu2025controllablegpt,
     title = {ControllableGPT: A Ground-Up Designed Controllable GPT for Molecule Optimization},
     author = {Liu, Xuefeng and Jiang, Songhao and Li, Bo and Stevens, Rick},
     journal = {arXiv preprint arXiv:2502.10631},
     year = {2025}
   }

2024

1. Preprint

   Reflections from the 2024 large language model (llm) hackathon for applications in materials science and chemistry

   Yoel Zimmermann, Adib Bazgir, Zartashia Afzal, and 8 more authors

   arXiv preprint arXiv:2411.15221, 2024

   Bib

   @article{zimmermann2024reflections,
     title = {Reflections from the 2024 large language model (llm) hackathon for applications in materials science and chemistry},
     author = {Zimmermann, Yoel and Bazgir, Adib and Afzal, Zartashia and Agbere, Fariha and Ai, Qianxiang and Alampara, Nawaf and Al-Feghali, Alexander and Ansari, Mehrad and Antypov, Dmytro and Aswad, Amro and others},
     journal = {arXiv preprint arXiv:2411.15221},
     year = {2024}
   }

2. ICLR

   Learning from imperfect human feedback: A tale from corruption-robust dueling

   Yuwei Cheng, Fan Yao, Xuefeng Liu, and 1 more author

   International Conference on Learning Representations, 2024

   Best Poster Award, Midwest ML Symposium 2024 Bib

   Best Poster Award, Midwest ML Symposium 2024

   @article{cheng2024learning,
     title = {Learning from imperfect human feedback: A tale from corruption-robust dueling},
     author = {Cheng, Yuwei and Yao, Fan and Liu, Xuefeng and Xu, Haifeng},
     journal = {International Conference on Learning Representations},
     year = {2024},
   }

3. Preprint

   Binding affinity prediction: From conventional to machine learning-based approaches

   Xuefeng Liu, Songhao Jiang, Xiaotian Duan, and 8 more authors

   arXiv preprint arXiv:2410.00709, 2024

   Bib

   @article{liu2024binding,
     title = {Binding affinity prediction: From conventional to machine learning-based approaches},
     author = {Liu, Xuefeng and Jiang, Songhao and Duan, Xiaotian and Vasan, Archit and Huang, Qinan and Liu, Chong and Li, Michelle M and Ma, Heng and Brettin, Thomas and Ramanathan, Arvind and others},
     journal = {arXiv preprint arXiv:2410.00709},
     year = {2024}
   }

4. Preprint

   Reflections from the 2024 large language model (llm) hackathon for applications in materials science and chemistry

   Yoel Zimmermann, Adib Bazgir, Zartashia Afzal, and 8 more authors

   arXiv preprint arXiv:2411.15221, 2024

   Bib

   @article{zimmermann2024reflectiont,
     title = {Reflections from the 2024 large language model (llm) hackathon for applications in materials science and chemistry},
     author = {Zimmermann, Yoel and Bazgir, Adib and Afzal, Zartashia and Agbere, Fariha and Ai, Qianxiang and Alampara, Nawaf and Al-Feghali, Alexander and Ansari, Mehrad and Antypov, Dmytro and Aswad, Amro and others},
     journal = {arXiv preprint arXiv:2411.15221},
     year = {2024}
   }

5. NeurIPS

   Contextual active model selection

   Xuefeng Liu, Fangfang Xia, Rick Stevens, and 1 more author

   Advances in Neural Information Processing Systems, 2024

   Bib

   @article{liu2024contextual,
     title = {Contextual active model selection},
     author = {Liu, Xuefeng and Xia, Fangfang and Stevens, Rick and Chen, Yuxin},
     journal = {Advances in Neural Information Processing Systems},
     volume = {37},
     pages = {49914--49956},
     year = {2024}
   }

6. ICML

   Entropy-reinforced planning with large language models for drug discovery

   Xuefeng Liu, Chih-chan Tien, Peng Ding, and 2 more authors

   International Conference on Machine Learning, 2024

   Oral at Midwest-AI4D3 Workshop 2025 Bib

   Oral

   @article{liu2024entropy,
     title = {Entropy-reinforced planning with large language models for drug discovery},
     author = {Liu, Xuefeng and Tien, Chih-chan and Ding, Peng and Jiang, Songhao and Stevens, Rick L},
     journal = {International Conference on Machine Learning},
     year = {2024},
   }

7. ICLR-ML4LMS

   Leveraging Protein Large Language Models and Graph Neural Networks for Binding Affinity Prediction

   Xuefeng Liu, Chih-chan Tien, Songhao Jiang, and 1 more author

   2024
8. ICLR-GenAI4DM

   APO: Advantage-alignment Policy Optimization for Fine-tuning Generative Models

   Xuefeng Liu, Songhao Jiang, Thomas Brettin, and 3 more authors

   2024

2023

1. SciRep

   AI-accelerated protein-ligand docking for SARS-CoV-2 is 100-fold faster with no significant change in detection

   Austin Clyde, Xuefeng Liu, Thomas Brettin, and 8 more authors

   Scientific reports, 2023
2. ICML

   Active policy improvement from multiple black-box oracles

   Xuefeng Liu, Takuma Yoneda, Chaoqi Wang, and 2 more authors

   In International Conference on Machine Learning, 2023

   Bib

   @inproceedings{liu2023active,
     title = {Active policy improvement from multiple black-box oracles},
     author = {Liu, Xuefeng and Yoneda, Takuma and Wang, Chaoqi and Walter, Matthew and Chen, Yuxin},
     booktitle = {International Conference on Machine Learning},
     pages = {22320--22337},
     year = {2023},
     organization = {PMLR}
   }

3. NeurIPS-AI4D3

   DRUGIMPROVER: Utilizing reinforcement learning for multi-objective alignment in drug optimization

   Xuefeng Liu, Songhao Jiang, Archit Vasan, and 6 more authors

   In NeurIPS 2023 Workshop on New Frontiers of AI for Drug Discovery and Development, 2023

   Oral at NeurIPS-AI4D3 2023 Bib

   Oral

   @inproceedings{liu2023drugimprover,
     title = {DRUGIMPROVER: Utilizing reinforcement learning for multi-objective alignment in drug optimization},
     author = {Liu, Xuefeng and Jiang, Songhao and Vasan, Archit and Brace, Alexander and Gokdemir, Ozan and Brettin, Thomas and Xia, Fangfang and Foster, Ian and Stevens, Rick},
     booktitle = {NeurIPS 2023 Workshop on New Frontiers of AI for Drug Discovery and Development},
     number = {3},
     pages = {8},
     year = {2023},
   }

4. ICLR

   Blending imitation and reinforcement learning for robust policy improvement

   Xuefeng Liu, Takuma Yoneda, Rick L Stevens, and 2 more authors

   International Conference on Learning Representations, 2023

   Spotlight Bib

   Top 5%

   @article{liu2023blending,
     title = {Blending imitation and reinforcement learning for robust policy improvement},
     author = {Liu, Xuefeng and Yoneda, Takuma and Stevens, Rick L and Walter, Matthew R and Chen, Yuxin},
     journal = {International Conference on Learning Representations},
     year = {2023},
   }

2022

1. ICML-ReALML

   Contextual active online model selection with expert advice

   Xuefeng Liu, Fangfang Xia, Rick L Stevens, and 1 more author

   In ICML2022 Workshop on Adaptive Experimental Design and Active Learning in the Real World, 2022

   Bib

   @inproceedings{liu2022contextual,
     title = {Contextual active online model selection with expert advice},
     author = {Liu, Xuefeng and Xia, Fangfang and Stevens, Rick L and Chen, Yuxin},
     booktitle = {ICML2022 Workshop on Adaptive Experimental Design and Active Learning in the Real World},
     year = {2022},
     organization = {ICML}
   }

2020

1. Preprint

   Targeting SARS-CoV-2 with AI-and HPC-enabled lead generation: A first data release

   Yadu Babuji, Ben Blaiszik, Tom Brettin, and 8 more authors

   arXiv preprint arXiv:2006.02431, 2020

   Bib

   @article{babuji2020targeting,
     title = {Targeting SARS-CoV-2 with AI-and HPC-enabled lead generation: A first data release},
     author = {Babuji, Yadu and Blaiszik, Ben and Brettin, Tom and Chard, Kyle and Chard, Ryan and Clyde, Austin and Foster, Ian and Hong, Zhi and Jha, Shantenu and Li, Zhuozhao and others},
     journal = {arXiv preprint arXiv:2006.02431},
     year = {2020}
   }