Sotabase

Career

· Senior Principal Research Scientist, Lawrence Livermore National Laboratory2025–
· Data Science Institute (DSI) Council Member, Lawrence Livermore National Laboratory2024–

Publications (182)

Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond
Neural Information Processing Systems · 2020
337
cited
A Primer on Zeroth-Order Optimization in Signal Processing and Machine Learning: Principals, Recent Advances, and Applications
IEEE Signal Processing Magazine · 2020
298
cited
TrustLLM: Trustworthiness in Large Language Models
arXiv.org · 2024
294
cited
Mix-n-Match: Ensemble and Compositional Methods for Uncertainty Calibration in Deep Learning
International Conference on Machine Learning · 2020
260
cited
Explainable machine learning in materials science
npj Computational Materials · 2022
256
cited
Zeroth-Order Stochastic Variance Reduction for Nonconvex Optimization
Neural Information Processing Systems · 2018
217
cited
Reliable and explainable machine-learning methods for accelerated material discovery
npj Computational Materials · 2019
168
cited
Anomalous Example Detection in Deep Learning: A Survey
IEEE Access · 2020
166
cited
Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
arXiv.org · 2025
144
cited
Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptions
arXiv.org · 2022
113
cited
NEFTune: Noisy Embeddings Improve Instruction Finetuning
International Conference on Learning Representations · 2023
110
cited
Shifting Attention to Relevance: Towards the Predictive Uncertainty Quantification of Free-Form Large Language Models
Annual Meeting of the Association for Computational Linguistics · 2023
106
cited
GTBench: Uncovering the Strategic Reasoning Limitations of LLMs via Game-Theoretic Evaluations
arXiv.org · 2024
97
cited
SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning
Conference on Empirical Methods in Natural Language Processing · 2024
94
cited
Generative Counterfactual Introspection for Explainable Deep Learning
IEEE Global Conference on Signal and Information Processing · 2019
93
cited
Distributed Bayesian Detection in the Presence of Byzantine Data
IEEE Transactions on Signal Processing · 2013
88
cited
G-PATE: Scalable Differentially Private Data Generator via Private Aggregation of Teacher Discriminators
Neural Information Processing Systems · 2019
88
cited
Data Falsification Attacks on Consensus-Based Detection Systems
IEEE Transactions on Signal and Information Processing over Networks · 2015
86
cited
Multi-Prize Lottery Ticket Hypothesis: Finding Accurate Binary Neural Networks by Pruning A Randomly Weighted Network
International Conference on Learning Representations · 2021
82
cited
A Winning Hand: Compressing Deep Networks Can Improve Out-Of-Distribution Robustness
Neural Information Processing Systems · 2021
80
cited
Sotabase