The full acceptance of Deep Learning (DL) models in the clinical field is rather low with
respect to the quantity of high-performing solutions reported in the literature. End users are …

Machine learning systems generally assume that the training and testing distributions are
the same. To this end, a key requirement is to develop models that can generalize to unseen …

A fundamental goal of scientific research is to learn about causal relationships. However,
despite its critical role in the life and social sciences, causality has not had the same …

Learning robust models that generalize well under changes in the data distribution is critical
for real-world applications. To this end, there has been a growing surge of interest to learn …

We study causal representation learning, the task of inferring latent causal variables and
their causal relations from high-dimensional functions (“mixtures”) of the variables. Prior …

Aligning large language models (LLMs) with human preferences through reinforcement
learning (RLHF) can lead to reward hacking, where LLMs exploit failures in the reward …

Machine learning models, while progressively advanced, rely heavily on the IID assumption,
which is often unfulfilled in practice due to inevitable distribution shifts. This renders them …

Logical reasoning is needed in a wide range of NLP tasks. Can a BERT model be trained
end-to-end to solve logical reasoning problems presented in natural language? We attempt …

Pre-trained language models (PLMs) have gained increasing popularity due to their
compelling prediction performance in diverse natural language processing (NLP) tasks …

Since out-of-distribution generalization is a generally ill-posed problem, various proxy
targets (eg, calibration, adversarial robustness, algorithmic corruptions, invariance across …