Yimeng Zeng

PhD Candidate

Computer Science
University of Pennsylvania

Email: [email protected]

Curriculum Vitae  /  GitHub  /  Google Scholar  /  X  /  LinkedIn

About Me

I am a fourth-year PhD candidate in the Department of Computer and Information Science at the University of Pennsylvania, advised by Jacob Gardner and Osbert Bastani. Previously, I completed my undergraduate degrees in Computer Science and Mathematics at Cornell University.

My research develops LLM-centric generative optimization methods, combining generative models (e.g., VAEs/LLMs) with Bayesian optimization (BO) to solve open-ended design problems efficiently. I focus on end-to-end, closed-loop systems that propose candidates, evaluate them, and learn from feedback. Applications include biomedical discovery (antibody/peptide design) and systems performance optimization (query planning and code optimization).

Research

* indicates equal contribution. See Google Scholar for a complete list of publications.

Topics: LLM · Optimization · Systems · Biology

LLMs & Learning-Based Optimization

• Scaling Multi-Task Bayesian Optimization with Large Language Models
  Yimeng Zeng, Natalie Maus, Haydn Thomas Jones, Jeffrey Tao, Fangping Wan, Marcelo Der Torossian Torres, Cesar de la Fuente-Nunez, Ryan Marcus, Osbert Bastani, Jacob R Gardner
  International Conference on Learning Representations (ICLR 2026)
  LLM · Optimization
• Purely Agentic Black-Box Optimization for Biological Design
  Natalie Maus, Yimeng Zeng, Haydn Thomas Jones, Yining Huang, Gaurav Ng Goel, Alden Rose, Kyurae Kim, Hyun-Su Lee, Marcelo Der Torossian Torres, Fangping Wan, Cesar de la Fuente-Nunez, Mark Yatskar, Osbert Bastani, Jacob R. Gardner
  arXiv preprint, 2026
  LLM · Optimization · Biology
• Self-Driving Datasets: From 20 Million Papers to Nuanced Biomedical Knowledge at Scale
  Haydn Jones, Yimeng Zeng, Alden Rose, Li S. Yifei, Yining Huang, Kaiwen Wu, Jiaming Liang, Maggie Ziyu Huan, Yoseph Barash, Cesar de la Fuente-Nunez, Osbert Bastani, Zachary Ives, Mark Yatskar, Jacob R. Gardner
  arXiv preprint, 2026
  LLM · Biology
• Zeroth-Order Fine-Tuning of LLMs with Transferable Static Sparsity
  Wentao Guo, Jikai Long, Yimeng Zeng, Zirui Liu, Xinyu Yang, Yide Ran, Jacob R. Gardner, Osbert Bastani, Christopher De Sa, Xiaodong Yu, Beidi Chen, Zhaozhuo Xu
  International Conference on Learning Representations (ICLR 2025)
  LLM · Optimization
• Learned Offline Query Planning via Bayesian Optimization
  Jeffrey Tao, Natalie Maus, Haydn Jones, Yimeng Zeng, Jacob R. Gardner, Ryan Marcus
  ACM SIGMOD International Conference on Management of Data (SIGMOD 2025) [code]
  LLM · Optimization · Systems
• Automated High-Level Code Optimization for Warehouse Performance
  Alexander Shypula, Aman Madaan, Yimeng Zeng, Uri Alon, Jacob Gardner, Milad Hashemi, Graham Neubig, Parthasarathy Ranganathan, Osbert Bastani, Amir Yazdanbakhsh
  IEEE Micro, "Top Picks" issue, 2025
  LLM · Systems
• Learning Performance-Improving Code Edits
  Alexander Shypula, Aman Madaan, Yimeng Zeng, Uri Alon, Jacob Gardner, Milad Hashemi, Graham Neubig, Parthasarathy Ranganathan, Osbert Bastani, Amir Yazdanbakhsh
  International Conference on Learning Representations (ICLR 2024) Spotlight [code]
  LLM · Systems

Bayesian Optimization & Scientific Design

• A Generative Artificial Intelligence Approach for Antibiotic Optimization
  Marcelo D. T. Torres*, Yimeng Zeng*, Fangping Wan*, Natalie Maus, Jacob Gardner, Cesar de la Fuente-Nunez
  Nature Machine Intelligence, 2026 [code]
  Optimization · Biology
• Multi-Objective Coverage Bayesian Optimization (MOCOBO)
  Natalie Maus, Kyurae Kim, Yimeng Zeng, Haydn Thomas Jones, Fangping Wan, Marcelo Der Torossian Torres, Cesar de la Fuente-Nunez, Jacob R. Gardner
  Advances in Neural Information Processing Systems (NeurIPS 2025) [poster]
  Optimization
• Generative Adversarial Model-Based Optimization via Source Critic Regularization
  Michael S. Yao, Yimeng Zeng, Hamsa Bastani, Jacob R. Gardner, James Gee, Osbert Bastani
  Advances in Neural Information Processing Systems (NeurIPS 2024) [slides] [poster] [code]
  Optimization
• Adversarial Query Synthesis via Bayesian Optimization
  Yimeng Zeng, Jeffrey Tao, Haydn Thomas Jones, Natalie Maus, Osbert Bastani, Jacob R. Gardner, Ryan Marcus
  NeurIPS ML for Systems Workshop 2025 [poster]
  Optimization · Systems
• Antibody Design with Constrained Bayesian Optimization
  Yimeng Zeng, Hunter Elliott, Phillip Maffettone, Peyton Greenside, Osbert Bastani, Jacob R. Gardner
  ICLR Workshop on Generative & Experimental Methods in Biology (GEMBio 2024) Oral Presentation [poster]
  Optimization · Biology
• Improving Structural Diversity of Black-Box LLMs via Chain-of-Specification Prompting
  Halley Young, Yimeng Zeng, Jacob Gardner, Osbert Bastani
  arXiv preprint, 2024
  LLM
• Inverse Protein Folding Using Deep Bayesian Optimization
  Natalie Maus*, Yimeng Zeng*, Daniel Allen Anderson, Phillip Maffettone, Aaron Solomon, Peyton Greenside, Osbert Bastani, Jacob R. Gardner
  arXiv preprint, 2023
  Optimization · Biology

Teaching

• Graduate Teaching Assistant, CIS 5200 Introduction to Machine Learning (Fall 2023)
• Graduate Teaching Assistant, CIS 6200 Advanced Topics in Machine Learning (Spring 2026)
• Undergraduate Teaching Assistant, CS 4780 Introduction to Machine Learning, Cornell University (2021-2022)

Service

Reviewer: NeurIPS 2024, ACL ARR (June 2024), NeurIPS 2025, ICLR 2026

Honors & Awards

• University of Pennsylvania Graduate Fellowship
• Cornell University Dean's List, College of Arts and Sciences (Fall 2019, Fall 2020)