Visually-grounded dialog systems, which integrate multiple modes of
comm...
Mixture-of-Experts models are commonly used when there exist distinct
cl...
Multi-object tracking (MOT) is a challenging vision task that aims to de...
Logo embedding plays a crucial role in various e-commerce applications b...
We present a new category of physics-informed neural networks called phy...
The phenomenon of seat occupancy in university libraries is a prevalent
...
Recently, several multi-modal models have been developed for joint image...
Millions of users are active on social media. To allow users to better
s...
Perceiving multi-modal information and fulfilling dialogues with humans ...
Large language models (LLMs) have exhibited an emergent in-context learn...
In this paper, we propose a selfdistillation framework with meta
learnin...
Recently, speech-text pre-training methods have shown remarkable success...
Cross-lingual and cross-domain knowledge alignment without sufficient
ex...
Entity alignment(EA) is a crucial task for integrating cross-lingual and...
Traditional multi-agent reinforcement learning algorithms are difficultl...
Open intent classification, which aims to correctly classify the known
i...
Deep learning techniques have dominated the literature on aspect-based
s...
Table-based reasoning has shown remarkable progress in combining deep mo...
Efficient detectors for edge devices are often optimized for metrics lik...
Math word problems (MWPs) is a task that automatically derives solution
...
Although Physics-Informed Neural Networks (PINNs) have been successfully...
In this paper, we propose a novel SQL guided pre-training framework STAR...
Existing benchmark datasets for recommender systems (RS) either are crea...
Recently, pre-training methods have shown remarkable success in task-ori...
Pre-training methods with contrastive learning objectives have shown
rem...
This paper aims to improve the performance of text-to-SQL parsing by
exp...
Text-to-SQL parsing is an essential and challenging task. The goal of
te...
Ovarian cancer is one of the most harmful gynecological diseases. Detect...
Deeply learned representations have achieved superior image retrieval
pe...
The importance of building text-to-SQL parsers which can be applied to n...
Temporal action detection (TAD) is extensively studied in the video
unde...
The adversarial robustness of a neural network mainly relies on two fact...
Deep image inpainting research mainly focuses on constructing various ne...
This paper offers a comprehensive review of the research on Natural Lang...
Pre-trained models have proved to be powerful in enhancing task-oriented...
Recently pre-training models have significantly improved the performance...
Complex Knowledge Base Question Answering is a popular area of research ...
Recovering programs' call graphs is crucial for inter-procedural analysi...
Deep neural networks (DNN) have achieved great success in the recommende...
Orthogonal time-frequency space (OTFS) has been confirmed to take advant...
Image Retrieval is a fundamental task of obtaining images similar to the...
Despite tremendous progress in missing data imputation task, designing n...
This ability to learn consecutive tasks without forgetting how to perfor...
Sequential recommender systems (SRS) have become a research hotspot due ...
Lifelong learning capabilities are crucial for sentiment classifiers to
...
Making accurate recommendations for cold-start users has been a longstan...
Most existing neural network based task-oriented dialogue systems follow...
Answer selection, which is involved in many natural language processing
...
Orthogonal time frequency space (OTFS) modulation has been confirmed to
...
Deep neural networks are vulnerable to semantic invariant corruptions an...