Mihaela van der Schaar

A new framework improves symbolic regression for complex data analysis.

A new method provides better feedback for training language models.

A new method combining language models with optimization strategies for improved performance.

This research combines Fourier analysis with diffusion models for better time series generation.

A new method enhances LLMs by integrating external knowledge for better performance.

Combining prior knowledge and adaptability enhances machine learning performance with limited data.

A look into the challenges and solutions for identifying hard samples.

DAGnosis improves data reliability by effectively identifying inconsistencies.

Importance of focusing on tabular data for machine learning advancements.

Introducing Alignment from Demonstrations for safe and effective language models.

DIPS addresses data quality issues in pseudo-labeling for better machine learning outcomes.

LaTable enhances the creation of synthetic tabular data across various fields.

A look at methods for estimating treatment effects using real-world data.

A new method enhances the accuracy of prediction intervals for reliable decision-making.

A new framework enhances disease prediction using diverse healthcare data.

Sparse Neural Networks streamline feature selection for better model performance.

A look at deep learning behaviors and their explanations.

Learn how small changes in input affect language model responses.

AI adapts to individual preferences using fewer examples, enhancing user interactions.