Kun Zhang

A new framework to classify images without prior labels using broad vocabulary.

A new method in machine learning enhances model adaptability across various data types.

A new model enhances student assessment through improved response analysis.

A new approach enhances recommendations by leveraging collaborative filtering and contrastive learning.

This work highlights dependencies between content and style in counterfactual generation.

Integrating language models into causal discovery streamlines analysis and reveals hidden relationships.

Methods to minimize bias in large language models for fairer outcomes.

This article presents a method to test independence in categorized data.

A new approach to ensure fairness in cognitive diagnosis using sensitive information.

Examining how fairness in machine learning can evolve across decisions and time.

Researchers enhance GNNs for better understanding of complex graph structures.

A new framework that enhances MLP performance in graph classification using GNN knowledge.

This study proposes a framework for understanding hidden concepts in complex data.

EQuAD improves model performance on graphs facing changing data distributions.

A model that improves predictions of critical health issues for better patient care.

A new method improves causal discovery accuracy using automated kernel selection.

A study on identifying causal relationships amidst hidden variables and measurement errors.

This paper discusses continual learning of causal relations without losing previous knowledge.

Recent studies show photon subtraction can improve the purity of Gaussian states.

A novel approach to understanding variable relationships in changing environments.

Learn the tactics behind sharing information in negotiations.

A novel method for efficient hyperparameter tuning and cost management in AI training.

Learn how causal discovery helps us connect different factors in various fields.