Scholar
Nate Gruver
Google Scholar ID: R5QNdhcAAAAJ
New York University
Citations & Impact
Citations
1,631
H-index
12
i10-index
12
Publications
14
Co-authors
12
list available
Publications
Resume (English only)
Academic Achievements
- Published multiple papers, including:
- - Understanding the relationship between large-scale pretraining and inductive biases
- - Generative modeling for protein and materials design
- - Combining generative models with uncertainty estimates
- Notable publications include:
- - Large Language Models Must Be Taught to Know What They Don't Know (NeurIPS 2024)
- - Fine-Tuned Language Models Generate Stable Inorganic Materials as Text (ICLR 2024)
- - Large Language Models Are Zero Shot Time Series Forecasters (NeurIPS 2023)
- - Protein Design with Guided Discrete Diffusion (NeurIPS 2023, Spotlight)
- - The Lie Derivative for Measuring Learned Equivariance (ICLR 2023, Oral)
- - On Feature Learning in the Presence of Spurious Correlations (NeurIPS 2022)
- - Accelerating Bayesian Optimization for Biological Sequence Design with Denoising Autoencoders (ICML 2022, short talk)
- - Deconstructing the Inductive Biases of Hamiltonian Neural Networks (ICLR 2022, Spotlight)
- - Effective Surrogate Models for Protein Design with Bayesian Optimization (ICML Workshop on Computational Biology 2021)
- - Epistemic Uncertainty in Learning Chaotic Dynamical Systems (ICML Uncertainty in Deep Learning Workshop 2021)
- - Disagreement-Regularized Imitation of Complex Multi-Agent Interactions (NeuRIPs, Machine Learning for Autonomous Driving Workshop 2020)
- - Multi-agent Adversarial Inverse Reinforcement Learning with Latent Variables (AAMAS 2020)
- - Online Stochastic Planning for Multimodal Sensing and Navigation under Uncertainty (ICAPS 2020)
Research Experience
- Internships at FAIR (generative modeling of crystals and proteins), Waymo (driver behavior modeling), and Google Cloud (applying ML to kernel virtual machines).
Education
- PhD from NYU Courant, advised by Andrew Gordon Wilson and working closely with Kyunghyun Cho. BS/MS in computer science from Stanford University, where he worked with Stefano Ermon, Mykel Kochenderfer, and Chris Piech.
Background
- Machine learning researcher focusing on generative modeling and scientific discovery.
Miscellany
- Email / Twitter / Google Scholar
