Erdun Gao

ActiveCQ: Active Estimation of Causal Quantities

Beyond DAGs: A Latent Partial Causal Model for Multimodal Learning

Concept Component Analysis: A Principled Approach for Concept Extraction in LLMs

I Predict Therefore I Am: Is Next Token Prediction Enough to Learn Human-Interpretable Concepts from Data?

Causal-EPIG: A Prediction-Oriented Active Learning Framework for CATE Estimation

TimeLAVA: Learning-Agnostic Valuation for Time Series Data

Towards Identifiable Latent Additive Noise Models

Identifying Unperturbed Cellular Programs Enables Accurate Single-Cell Perturbation Prediction

On the Value of Cross-Modal Misalignment in Multimodal Representation Learning

MissScore: High-Order Score Estimation in the Presence of Missing Data

MissScore: High-Order Score Estimation in the Presence of Missing Data