Few-shot learning (FSL) has emerged as an effective learning method and shows great
potential. Despite the recent creative works in tackling FSL tasks, learning valid information …

Recent decades have seen a rise in the use of physics methods to study different societal
phenomena. This development has been due to physicists venturing outside of their …

Large transformer-based models are able to perform in-context few-shot learning, without
being explicitly trained for it. This observation raises the question: what aspects of the …

The pursuit of artificial general intelligence (AGI) continuously demands higher computing
performance. Despite the superior processing speed and efficiency of integrated photonic …

Computer vision now relies on data, but we know surprisingly little about what factors in the
data affect performance. We argue that this stems from the way data is collected. Designing …

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 …

Transformer models exhibit in-context learning: the ability to accurately predict the response
to a novel query based on illustrative examples in the input sequence. In-context learning …

People can learn a new concept and use it compositionally, understanding how to" blicket
twice" after learning how to" blicket." In contrast, powerful sequence-to-sequence (seq2seq) …

Cell-line screens create expansive datasets for learning predictive markers of drug
response, but these models do not readily translate to the clinic with its diverse contexts and …

Deep reinforcement learning has gathered much attention recently. Impressive results were
achieved in activities as diverse as autonomous driving, game playing, molecular …