Previous studies have typically assumed that large language models are u...
Vision-language pre-training (VLP) methods are blossoming recently, and ...
Catastrophic forgetting (CF) is a phenomenon that occurs in machine lear...
The emergence of self-supervised representation (i.e., wav2vec 2.0) allo...
In-Batch contrastive learning is a state-of-the-art self-supervised meth...
Large pre-trained models (LPMs), such as LLaMA and ViT-G, have shown
exc...
Multi-task learning has been widely applied in computational vision, nat...
Task-incremental continual learning refers to continually training a mod...
Representation forgetting refers to the drift of contextualized
represen...
Few-shot named entity recognition (NER) systems aims at recognizing new
...
Contrastive Language-Image Pre-training, benefiting from large-scale
unl...
Pre-trained wav2vec2.0 model has been proved its effectiveness for speak...
Multi-view 3D object detection (MV3D-Det) in Bird-Eye-View (BEV) has dra...
In this paper, we propose an active reconfigurable intelligent surface (...
We report the result of the first edition of the WMT shared task on
Tran...
Semi-supervised semantic segmentation requires the model to effectively
...
Word alignment which aims to extract lexicon translation equivalents bet...
The physical layer security (PLS) is investigated for reconfigurable
int...
Word-level Quality Estimation (QE) of Machine Translation (MT) aims to f...
We present ONCE-3DLanes, a real-world autonomous driving dataset with la...
Generating adversarial examples for Neural Machine Translation (NMT) wit...
We present Laneformer, a conceptually simple yet powerful transformer-ba...
Complete Multi-lingual Neural Machine Translation (C-MNMT) achieves supe...
Causal Emotion Entailment (CEE) aims to discover the potential causes be...
Road user behavior prediction is one of the most critical components in
...
Translation Suggestion (TS), which provides alternatives for specific wo...
Context: Stack Overflow is very helpful for software developers who are
...
Mainstream lane marker detection methods are implemented by predicting t...
Code comment has been an important part of computer programs, greatly
fa...
Most end-to-end Multi-Object Tracking (MOT) methods face the problems of...
LiDAR based 3D object detectors typically need a large amount of
detaile...
Unsupervised domain adaptation enables intelligent models to transfer
kn...
Multiple Sclerosis (MS) is a chronic, inflammatory and degenerative
neur...
Graph Neural Networks (GNNs) have achieved tremendous success in graph
r...
As a more practical setting for unsupervised domain adaptation, Universa...
This paper proposes a new pre-training method, called Code-Switching
Pre...
Graph representation learning has been extensively studied in recent yea...
Domain alignment (DA) has been widely used in unsupervised domain adapta...
This paper proposes a hybrid-relaying scheme empowered by a self-sustain...
Entropy minimization has been widely used in unsupervised domain adaptat...
Electrocardiography plays an essential role in diagnosing and screening
...
The new demands for high-reliability and ultra-high capacity wireless
co...
With non-orthogonal multiple access(NOMA), we tackle the maximization of...
In this work, we propose a novel beamforming design to enhance physical ...
Unsupervised neural machine translation (NMT) is a recently proposed app...
In this letter, to break the limit of the traditional linear models for ...
In this paper, we propose novel strategies for neutral vector variable
d...
This paper proposes an approach for applying GANs to NMT. We build a
con...