Scholar
Lily H. Zhang
Google Scholar ID: fmCi9ZQAAAAJ
New York University
Citations & Impact
Citations
451
H-index
9
i10-index
9
Publications
19
Co-authors
0
Resume (English only)
Academic Achievements
- - Publications:
- - Preference Learning Algorithms Do Not Learn Preference Rankings, NeurIPS 2024
- - Robust Anomaly Detection for Particle Physics Using Multi-Background Representation Learning, MLST 2024
- - Towards Minimal Targeted Updates of Language Models with Targeted Negative Training, TMLR 2024
- - Don't Blame Dataset Shift! Shortcut Learning due to Gradients and Cross Entropy, NeurIPS 2023
- - When More is Less: Incorporating Additional Datasets Can Hurt Performance By Introducing Spurious Correlations, MLHC 2023
- - Robustness to Spurious Correlations Improves Semantic Out-of-Distribution Detection, AAAI 2023
- - Set Norm and Equivariant Residual Connections: Putting the Deep in Deep Sets, ICML 2022
- - Out-of-Distribution Generalization in the Presence of Nuisance-Induced Spurious Correlations, ICLR 2022
- - Understanding Out-of-Distribution Detection with Deep Generative Models, ICML 2021
- - Rapid Model Comparison by Amortizing Across Models, AABI 2020
- - Awards: JP Morgan PhD Fellow (2024), Meta AI Mentorship Fellow (2024), DeepMind Fellow (2020), Phi Beta Kappa (2017)
- - Patent: Graphical user interface systems for generating hierarchical data extraction training dataset.
Research Experience
- - Collaborated with Professors Kyle Cranmer (Physics), Kyunghyun Cho (Computer Science), Don Rubin (Statistics), Gary King (Quantitative Social Science), Jukka-Pekka “JP” Onnela (Biostatistics), John M. Higgins (Pathology, Systems Biology), and Dustin Tingley (Government, Political Science).
- - Worked for several machine learning start-ups and conducted LLM research at Google.
Education
- - New York University: Candidate for Doctor of Philosophy in Data Science, Aug. 2020 – Summer 2025 (projected), Advisor: Professor Rajesh Ranganath.
- - Harvard College: Bachelor of Arts in Statistics and Computer Science, Magna Cum Laude with High Honors, Aug. 2013 – May 2017.
Background
- - Research Interests: Advancing the reliability of machine learning models, including controllable generation and alignment of generative models, out-of-distribution detection, and generalization.
- - Application Areas: Health and science.
- - Honors: DeepMind Scholar, Visiting Researcher at Facebook AI Research, JP Morgan Chase PhD Fellow.
Co-authors