We study neural network loss landscapes through the lens of mode connectivity, the
observation that minimizers of neural networks retrieved via training on a dataset are …

Instruction tuning plays a critical role in aligning large language models (LLMs) with human
preference. Despite the vast amount of open instruction datasets, naively training a LLM on …

Large web-sourced multimodal datasets have powered a slew of new methods for learning
general-purpose visual representations, advancing the state of the art in computer vision …

As the number of large language models (LLMs) released to the public grows, there is a
pressing need to understand the safety implications associated with these models learning …

While most machine learning models can provide confidence in their predictions, confidence
is insufficient to understand a prediction's reliability. For instance, the model may have a low …

Sample selection is a prevalent method in learning with noisy labels, where small-loss data
are typically considered as correctly labeled data. However, this method may not effectively …

Recent efforts at explaining the interplay of memorization and generalization in deep
overparametrized networks have posited that neural networks $\textit {memorize} $" hard" …

Data quality is crucial for robust machine learning algorithms, with the recent interest in data-
centric AI emphasizing the importance of training data characterization. However, current …

Early stopping methods in deep learning face the challenge of balancing the volume of
training and validation data, especially in the presence of label noise. Concretely, sparing …

Deep neural networks are over-parameterized and easily overfit the datasets they train on.
In the extreme case, it has been shown that these networks can memorize a training set with …