Large language models of code (Code-LLMs) have recently brought tremendo...
Fine-tuning pretrained models for automatically summarizing doctor-patie...
First-order methods for stochastic optimization have undeniable relevanc...
Structured prediction is often approached by training a locally normaliz...
The majority of current object detectors lack context: class predictions...
Neural architecture search methods are able to find high performance dee...
Beam search is widely used for approximate decoding in structured predic...
In deep learning, performance is strongly affected by the choice of
arch...
In this paper we propose a multi-convex framework for multi-task learnin...