The recommendation ecosystem involves interactions between recommender
s...
Stochastic gradient descent (SGD) performed in an asynchronous manner pl...
Sequential recommendation demonstrates the capability to recommend items...
Text classification is a fundamental task for natural language processin...
Recommender systems are important for providing personalized services to...
Seeing is believing, however, the underlying mechanism of how human visu...
Due to the nature of risk management in learning applicable policies,
ri...
Large Language Models (LLMs) are gaining increasing attention due to the...
Pronunciation assessment is a major challenge in the computer-aided
pron...
In this paper, we propose a general deep learning training framework XGr...
Deep learning is experiencing a rise in foundation models that are expec...
Understanding the evolution of online news communities is essential for
...
Text classification tasks often encounter few shot scenarios with limite...
In this paper, we propose DiffusionNER, which formulates the named entit...
In dynamic interaction graphs, user-item interactions usually follow
het...
How to behave efficiently and flexibly is a central problem for understa...
Genes are fundamental for analyzing biological systems and many recent w...
Solving complicated AI tasks with different domains and modalities is a ...
The intrinsic rotation invariance lies at the core of matching point clo...
As a common way of emotion signaling via non-linguistic vocalizations, v...
With the global population aging rapidly, Alzheimer's disease (AD) is
pa...
Conventional reinforcement learning (RL) needs an environment to collect...
Monitoring and analyzing stereotypical behaviours is important for early...
The collaborative filtering (CF) problem with only user-item interaction...
Ensemble methods can deliver surprising performance gains but also bring...
Practical networks for edge devices adopt shallow depth and small
convol...
Neural architecture search (NAS) has made tremendous progress in the
aut...
TAPS is a Topology-Aware intra-operator Parallelism strategy Searching
a...
Pure transformers have shown great potential for vision tasks recently.
...
Prompt learning is one of the most effective and trending ways to adapt
...
Novel artificial intelligence (AI) technology has expedited various
scie...
Many Click-Through Rate (CTR) prediction works focused on designing adva...
While person Re-identification (Re-ID) has progressed rapidly due to its...
In recent years, person Re-identification (ReID) has rapidly progressed ...
Dialogue summarization aims to condense the lengthy dialogue into a conc...
Dynamic interaction graphs have been widely adopted to model the evoluti...
A good state representation is crucial to solving complicated reinforcem...
Prompt learning is an effective paradigm that bridges gaps between the
p...
Vision transformers have shown excellent performance in computer vision
...
Recently privacy concerns of person re-identification (ReID) raise more ...
Autoregressive generative models are commonly used, especially for those...
Vector graphics (VG) have been ubiquitous in our daily life with vast
ap...
Offline reinforcement learning (RL) aims at learning policies from previ...
Foundation models are becoming the dominant deep learning technologies.
...
Sentence scoring aims at measuring the likelihood score of a sentence an...
CTR prediction has been widely used in the real world. Many methods mode...
Convolutional neural network (CNN) has achieved impressive success in
co...
Capturing the dynamics in user preference is crucial to better predict u...
In large-scale online services, crucial metrics, a.k.a., key performance...
The further development of deep neural networks is hampered by the limit...