![]() |
Zhen LinJump Trading |
I am a Quant Researcher at Jump Trading. I finished my Ph.D. at the University of Illinois at Urbana-Champaign, supervised by Professor Jimeng Sun. My latest research interest is in uncertainty quantification for language models and other generative models. I was fortunate to be recognized as a 2023 Meta PhD Fellowship Finalist.
Before grad school, I received my bachelor’s degrees in Computer Science, Mathematics, and Statistics from UChicago in 2018. I also spent two years at AQR Capital Management LLC.
Tutorial: Uncertainty Quantification and Confidence Calibration in Large Language Models: A Survey |
Contextualized Sequence Likelihood: Enhanced Confidence Scores for Natural Language Generation |
Generating with Confidence: Uncertainty Quantification for Black-box Large Language
Models |
Fast Online Value-Maximizing Prediction Sets with Conformal Cost Control |
Taking a Step Back with KCal: Multi-Class Kernel-Based Calibration for Deep Neural
Networks |
Conformal Prediction with Temporal Quantile Adjustments |
Conformal Prediction Intervals with Temporal Dependence |
SCRIB: Set-classifier with Class-specific Risk Bounds for Blackbox Models |
Locally Valid and Discriminative Prediction Intervals for Deep Learning Models |
Clebsch-Gordan Networks: A Fully Fourier Space Spherical Convolutional Neural
Network |
† denotes alphabetical author ordering |