2 citations · 3 across the 4 of their papers we have counts for
4 papers
Prefix-Safe Bayesian Belief Tracking for LLM Reasoning Reliability:Separating Calibration from Ranking
Zhenghan Song, Yunyi Li, Yulong Liu
Long reasoning traces need reliability estimates before final answers are known. We study prefix-conditioned eventual-success estimation, , using prefix-safe o…
Your Simulation Runs but Solves the Wrong Physics: PDE-Grounded Intent Verification for LLM-Generated Multiphysics Simulation Code
Zhenghan Song, Yulong Liu, Cheng Wan +4
Execution-based evaluation of LLM-generated code implicitly treats successful execution as a proxy for correctness. In scientific simulation, this proxy is insufficient: a generate…
Partially Interpretable Estimators (PIE): Black-Box-Refined Interpretable Machine Learning
Tong Wang, Jingyi Yang, Yunyi Li +1
We propose Partially Interpretable Estimators (PIE) which attribute a prediction to individual features via an interpretable model, while a (possibly) small part of the PIE predict…
Next Hit Predictor - Self-exciting Risk Modeling for Predicting Next Locations of Serial Crimes
Yunyi Li, Tong Wang
Our goal is to predict the location of the next crime in a crime series, based on the identified previous offenses in the series. We build a predictive model called Next Hit Predic…