Motivated by the efficiency and rapid convergence of pre-trained models ...
Neural Implicit Representations (NIR) have gained significant attention
...
Recent neural architecture search (NAS) frameworks have been successful ...
Open-Domain Conversational Question Answering (ODConvQA) aims at answeri...
Portrait stylization, which translates a real human face image into an
a...
Language models have achieved impressive performances on dialogue genera...
Large Language Models (LLMs) have shown promising performance in
knowled...
Distillation-aware Neural Architecture Search (DaNAS) aims to search for...
Neural Architecture Search (NAS) has emerged as a powerful technique for...
Distillation from Weak Teacher (DWT) is a method of transferring knowled...
We propose an approach to neural network weight encoding for generalizat...
Emotional Text-To-Speech (TTS) is an important task in the development o...
There has been a surge of interest in utilizing Knowledge Graphs (KGs) f...
Token-based masked generative models are gaining popularity for their fa...
In this paper, we introduce a novel learning scheme named weakly
semi-su...
Inspired by Regularized Lottery Ticket Hypothesis (RLTH), which states t...
Conversational Question Answering (ConvQA) models aim at answering a que...
Generation of graphs is a major challenge for real-world tasks that requ...
Self-supervised Video Representation Learning (VRL) aims to learn
transf...
There has been a significant progress in Text-To-Speech (TTS) synthesis
...
Existing adversarial learning methods for enhancing the robustness of de...
Recently, unsupervised adversarial training (AT) has been extensively st...
Transformer-based Language Models (LMs) achieve remarkable performances ...
Masked image modeling (MIM) has become a popular strategy for self-super...
Inspired by Regularized Lottery Ticket Hypothesis (RLTH), which hypothes...
Previous works have established solid foundations for neural set functio...
We propose StyleTalker, a novel audio-driven talking head generation mod...
In this work, we propose a novel uncertainty-aware object detection fram...
In this paper, we introduce a novel approach for systematically solving
...
Neural network quantization aims to transform high-precision weights and...
In real-world scenarios, subgraphs of a larger global graph may be
distr...
Real-time video segmentation is a crucial task for many real-world
appli...
Meta-learning approaches enable machine learning systems to adapt to new...
While deep reinforcement learning methods have shown impressive results ...
Pre-trained language models (PLMs) have achieved remarkable success on
v...
Dense retrieval models, which aim at retrieving the most relevant docume...
In practical federated learning scenarios, the participating devices may...
Self-supervised learning of graph neural networks (GNNs) aims to learn a...
Generating graph-structured data requires learning the underlying
distri...
In real-world federated learning scenarios, participants could have thei...
Dense computer vision tasks such as object detection and segmentation re...
The Mixup scheme suggests mixing a pair of samples to create an augmente...
Many applications that utilize sensors in mobile devices and apply machi...
Continual learning (CL) aims to learn a sequence of tasks without forget...
Numerous recent works utilize bi-Lipschitz regularization of neural netw...
Multilingual models jointly pretrained on multiple languages have achiev...
Many gradient-based meta-learning methods assume a set of parameters tha...
Recently, utilizing reinforcement learning (RL) to generate molecules wi...
Network quantization, which aims to reduce the bit-lengths of the networ...
Despite the success of recent Neural Architecture Search (NAS) methods o...