Hao Zou

Transformers with Endogenous In-Context Learning: Bias Characterization and Mitigation

Scalable Bayesian Active Learning with Batch Acquisition under Distribution Shift

Identifying Outcome-Oriented Root Causes via Cross Regression

Adaptive Marginal Sensitivity with Limited RCT Data for CATE Estimation

Understanding the Generalization of In-Context Learning in Transformers: An Empirical Study

Error Slice Discovery via Manifold Compactness

Effective and Efficient Time-Varying Counterfactual Prediction with State-Space Models

Learning Time-shared Hidden Heterogeneity for Counterfactual Outcome Forecast

FacLens: Transferable Probe for Foreseeing Non-Factuality in Large Language Models