Widely used alignment techniques, such as reinforcement learning from human feedback
(RLHF), rely on the ability of humans to supervise model behavior-for example, to evaluate …

Pseudo labeling and consistency regularization approaches with confidence-based
thresholding have made great progress in semi-supervised learning (SSL). In this paper, we …

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 …

Self-training methods have gained significant attention in recent years due to their
effectiveness in leveraging small labeled datasets and large unlabeled observations for …

Mainstream approaches for unsupervised domain adaptation (UDA) learn domain-invariant
representations to narrow the domain shift, which are empirically effective but theoretically …

Test-time adaptation (TTA) refers to adapting neural networks to distribution shifts,
specifically with just access to unlabeled test samples from the new domain at test-time …

Self-training algorithms, which train a model to fit pseudolabels predicted by another
previously-learned model, have been very successful for learning with unlabeled data using …

Strong student models can learn from weaker teachers: when trained on the predictions of a
weaker model, a strong pretrained student can learn to correct the weak model's errors and …

While deep learning models have shown remarkable performance in various tasks, they are
susceptible to learning non-generalizable _spurious features_ rather than the core features …

A fundamental challenge of over-parameterized deep learning models is learning
meaningful data representations that yield good performance on a downstream task without …