This paper presents AutoHint, a novel framework for automatic prompt
eng...
Named entity recognition (NER) is a crucial task for online advertisemen...
Diffusion models have gained significant attention in the realm of image...
Recent studies have shown that dual encoder models trained with the
sent...
Many natural language processing (NLP) tasks rely on labeled data to tra...
Learning transferable representation of knowledge graphs (KGs) is challe...
The dual-encoder has become the de facto architecture for dense retrieva...
Transformer models have achieved superior performance in various natural...
Knowledge distillation is often used to transfer knowledge from a strong...
Commonsense generation aims to generate a realistic sentence describing ...
Knowledge distillation is an effective way to transfer knowledge from a
...
Given an unexpected change in the output metric of a large-scale system,...
Extreme Classification (XC) seeks to tag data points with the most relev...
Non-Autoregressive generation is a sequence generation paradigm, which
r...
Delivering timely status updates in a timeliness-critical communication
...
Sparsely activated models (SAMs), such as Mixture-of-Experts (MoE), can
...
Pre-trained language models have led to substantial gains over a broad r...
Transformer is an attention-based neural network, which consists of two
...
Spinal codes are known to be capacity achieving over both the additive w...
Commonsense generation aims at generating plausible everyday scenario
de...
In a sponsored search engine, generative retrieval models are recently
p...
This paper examines the challenging problem of learning representations ...
Pre-trained language models like BERT have achieved great success in a w...
This paper proposes a new framework to solve the problem of monocular vi...
The long-haul communication systems can offer ultra high-speed data tran...
Rapid advances in GPU hardware and multiple areas of Deep Learning open ...