Neural sequence models based on the transformer architecture have demonstrated
remarkable\emph {in-context learning}(ICL) abilities, where they can perform new tasks …

In-context learning (ICL) is a type of prompting where a transformer model operates on a
sequence of (input, output) examples and performs inference on-the-fly. In this work, we …

Abstract Machine-learning models for medical tasks can match or surpass the performance
of clinical experts. However, in settings differing from those of the training dataset, the …

The world provides us with data of multiple modalities. Intuitively, models fusing data from
different modalities outperform their uni-modal counterparts, since more information is …

In recent years, prompt tuning has sparked a research surge in adapting pre-trained models.
Unlike the unified pre-training strategy employed in the language field, the graph field …

The focus of recent meta-learning research has been on the development of learning
algorithms that can quickly adapt to test time tasks with limited data and low computational …

It has become standard to solve NLP tasks by fine-tuning pre-trained language models
(LMs), especially in low-data settings. There is minimal theoretical understanding of …

Abstract The Federated Averaging (FedAvg) algorithm, which consists of alternating
between a few local stochastic gradient updates at client nodes, followed by a model …

Given the ubiquity of deep neural networks, it is important that these models do not reveal
information about sensitive data that they have been trained on. In model inversion attacks …

We provide new statistical guarantees for transfer learning via representation learning--
when transfer is achieved by learning a feature representation shared across different tasks …