For the two-layer shallow water equations, a high-order compact gas-kine...
In the previous studies, the high-order gas-kinetic schemes (HGKS) have
...
In this paper, an implicit unified gas-kinetic wave-particle method is
d...
The current optical communication systems minimize bit or symbol errors
...
Neural Radiance Field (NeRF) is a powerful tool to faithfully generate n...
We propose a novel image retouching method by modeling the retouching pr...
Textual logical reasoning, especially question answering (QA) tasks with...
Graph contrastive learning (GCL), as a popular approach to graph
self-su...
Approaches for the stance classification task, an important task for
und...
While conversational semantic role labeling (CSRL) has shown its usefuln...
In this paper, a third order gas kinetic scheme is developed on the thre...
Conversational semantic role labeling (CSRL) is believed to be a crucial...
Resolving pronouns to their referents has long been studied as a fundame...
We consider using untrained neural networks to solve the
reconstruction ...
In this paper, the compact gas-kinetic scheme for compressible flow is
e...
Language models like BERT and SpanBERT pretrained on open-domain data ha...
(Partial) ranking loss is a commonly used evaluation measure for multi-l...
Semantic role labeling (SRL) aims to extract the arguments for each pred...
We investigate video-aided grammar induction, which learns a constituenc...
Graph Neural Networks (GNNs) have recently shown to be powerful tools fo...
The task of graph-to-text generation aims at producing sentences that
pr...
In this paper, a third-order compact gas-kinetic scheme (GKS) on unstruc...
Character linking, the task of linking mentioned people in conversations...
This technique report introduces TexSmart, a text understanding system t...
The task of dialogue rewriting aims to reconstruct the latest dialogue
u...
The learning and evaluation of energy-based latent variable models (EBLV...
Score matching (SM) provides a compelling approach to learn energy-based...
In this paper, the unified gas-kinetic wave-particle (UGKWP) method is
f...
In this paper an even higher-order compact GKS up to sixth order of accu...
For multi-turn dialogue rewriting, the capacity of effectively modeling ...
In this paper, the unified gas-kinetic wave-particle (UGKWP) method has ...
Weakly supervised phrase grounding aims at learning region-phrase
corres...
The flow regime of micro flow varies from collisionless regime to
hydrod...
Deep learning models on graphs have achieved remarkable performance in
v...
Commonsense knowledge graphs (CKG) like Atomic and ASER are substantiall...
Adversarial training (AT) is one of the most effective defenses to impro...
Existing entity alignment methods mainly vary on the choices of encoding...
Conventional word embeddings represent words with fixed vectors, which a...
Generative adversarial networks (GANs) have shown promise in image gener...
Analysis of large-scale sequential data has been one of the most crucial...
Graph kernels are widely used for measuring the similarity between graph...
Generative adversarial networks (GANs) have made significant progress on...
It has been widely recognized that adversarial examples can be easily cr...
Numerical modeling of fluid flows based on kinetic equations provides an...
In this paper, we present a generic and robust multimodal synthesis syst...
In this paper, a simple and efficient third-order weighted essentially
n...
Recently, optical neural networks (ONNs) integrated in photonic chips ha...
Self-explaining text categorization requires a classifier to make a
pred...
Deep generative models (DGMs) have shown promise in image generation.
Ho...
Previous cross-lingual knowledge graph (KG) alignment studies rely on en...