Large language models (LLMs) have made significant strides in various ta...
Transformers for graph data are increasingly widely studied and successf...
Large language models (LLMs) can achieve highly effective performance on...
Many natural language processing (NLP) tasks rely on labeled data to tra...
We identify and overcome two key obstacles in extending the success of
B...
In this paper, we propose a large-scale language pre-training for text
G...
Long-form numerical reasoning in financial analysis aims to generate a
r...
Real-time air pollution monitoring is a valuable tool for public health ...
In the scenario of unsupervised extractive summarization, learning
high-...
Most existing pre-trained language representation models (PLMs) are
sub-...
Knowledge distillation is an effective way to transfer knowledge from a
...
Semantic segmentation is a popular research topic in computer vision, an...
Vascular segmentation extracts blood vessels from images and serves as t...
Contrastive-based self-supervised learning methods achieved great succes...
Due to the pivotal role of Recommender Systems (RS) in guiding customers...
The extraction of text information in videos serves as a critical step
t...
Extracting expressive visual features is crucial for accurate
Click-Thro...
This paper introduces a post-training quantization (PTQ) method achievin...
We present BN-NAS, neural architecture search with Batch Normalization
(...
In this paper, we observe two levels of redundancies when applying visio...
We introduce the first Neural Architecture Search (NAS) method to find a...
Automatic code summarization frees software developers from the heavy bu...
Online gaming is a multi-billion-dollar industry, which is growing faste...
Dilation convolution is a critical mutant of standard convolution neural...
Pedestrian detection in crowd scenes poses a challenging problem due to ...
The automation of neural architecture design has been a coveted alternat...
Recently, deep learning has been utilized to solve video recognition pro...
Several variants of stochastic gradient descent (SGD) have been proposed...
Automatic search of Quantized Neural Networks has attracted a lot of
att...
The recent progress on automatically searching augmentation policies has...
One-shot NAS method has attracted much interest from the research commun...
Recommendation Systems (RS) have become an essential part of many online...
The allocation of computation resources in the backbone is a crucial iss...
Click-Through Rate (CTR) prediction has been an indispensable component ...
There is a growing interest in automated neural architecture search (NAS...
Designing an effective loss function plays an important role in visual
a...
Data augmentation is critical to the success of modern deep learning
tec...
Convolutional Neural Networks(CNNs) are both computation and memory inte...