Purely Agentic Black-Box Optimization for Biological Design
natalie-maus
Education
PhD Computer Science
2025-08
University of Pennsylvania
MS Biomedical Informatics
2023-08
2025-05
Harvard Medical School
BS Computer Science & Statistics
2019-09
2023-06
Northwestern University
Interests
Agentic AI
Large Language Models
AI for Science
Generative Models
Protein Design
My Research 🎓
I am working on advancing scientific research with agentic AI. I am also interested in AI for science.
Featured Publications
•
•
1 min read
Multi-Scale Representation Learning for Protein Fitness Prediction
zuobai-zhang
Recent Publications
(2026).
Purely Agentic Black-Box Optimization for Biological Design.
arXiv.
(2025).
Few-shot Protein Fitness Prediction via In-context Learning and Test-time Training.
NeurIPS 2025 Workshop.
(2024).
Navigating Chemical Space with Latent Flows.
NeurIPS 2024.
(2024).
Multi-Scale Representation Learning for Protein Fitness Prediction.
NeurIPS 2024.
(2024).
Augmenting Evolutionary Models with Structure-Based Retrieval.
ICML 2024 Workshop.