Aadyot Bhatnagar — accepted AI-conference papers

2025

Scaling Unlocks Broader Generation and Deeper Functional Understanding of Proteins

Aadyot Bhatnagar, Sarthak Jain, Joel Beazer, Samuel C. Curran, Alexander M. Hoffnagle, Kyle Shan Ching +4

NeurIPS 2025spotlight

Generative protein language models (PLMs) are powerful tools for designing proteins purpose-built to solve problems in medicine, agriculture, and industrial processes. Recent work has trained ever larger language models, but there has been little systematic study of the optimal training distribution…

Cited by 0 Source ↗Scholar ↗

2023

Improved Online Conformal Prediction via Strongly Adaptive Online Learning

Aadyot Bhatnagar, Huan Wang, Caiming Xiong, Yu Bai

ICML 2023poster

We study the problem of uncertainty quantification via prediction sets, in an online setting where the data distribution may vary arbitrarily over time. Recent work develops *online conformal prediction* techniques that leverage regret minimization algorithms from the online learning literature to l…

Cited by 65 Source ↗PDF ↗code ↗Scholar ↗

2022

Local calibration: metrics and recalibration

Rachel Luo, Aadyot Bhatnagar, Yu Bai, Shengjia Zhao, Huan Wang, Caiming Xiong +4

UAI 2022poster

Probabilistic classifiers output confidence scores along with their predictions, and these confidence scores should be calibrated, i.e., they should reflect the reliability of the prediction. Confidence scores that minimize standard metrics such as the expected calibration error (ECE) accurately mea…

Cited by 23 Source ↗PDF ↗Scholar ↗