Data-centric AI, with its primary focus on the collection, management, a...
Controllable text generation is a fundamental aspect of natural language...
Constructing commonsense knowledge graphs (CKGs) has attracted wide rese...
Graph condensation, which reduces the size of a large-scale graph by
syn...
In the constant updates of the product dialogue systems, we need to retr...
Graph neural architecture search (NAS) has gained popularity in automati...
Harvesting question-answer (QA) pairs from customer service chatlog in t...
kNN-MT presents a new paradigm for domain adaptation by building an exte...
Modality representation learning is an important problem for multimodal
...
Solid-state LiDARs are more compact and cheaper than the conventional
me...
Recent years have witnessed fast developments of graph neural networks (...
Face recognition has been greatly facilitated by the development of deep...
Recently, kNN-MT has shown the promising capability of directly
incorpor...
kNN-MT, recently proposed by Khandelwal et al. (2020a), successfully com...
LiDAR odometry plays an important role in self-localization and mapping ...
In open domain table-to-text generation, we notice that the unfaithful
g...
Compression and efficient storage of neural network (NN) parameters is
c...
The prior work on natural language inference (NLI) debiasing mainly targ...
Many recent studies have shown that for models trained on datasets for
n...
Due to limited size and imperfect of the optical components in a
spectro...
This paper studies the estimation and inference of the quantile treatmen...
Facial attribute analysis has received considerable attention with the
d...
Despite the success of deep learning on many fronts especially image and...