Data analysis is challenging as it requires synthesizing domain knowledg...
With most modern visualization tools, authors need to transform their da...
Recent strides in neural speech synthesis technologies, while enjoying
w...
Audio deepfake detection is an emerging active topic. A growing number o...
The rhythm of synthetic speech is usually too smooth, which causes that ...
Large language models achieve state-of-the-art performance on sequence
g...
Current fake audio detection algorithms have achieved promising performa...
Applying Reinforcement Learning (RL) to sequence generation models enabl...
Recently, large vision model, Segment Anything Model (SAM), has
revoluti...
Large Language Models (LLMs) have shown remarkable aptitude in code
gene...
Self-supervised speech models are a rapidly developing research topic in...
Audio deepfake detection is an emerging topic in the artificial intellig...
Current fake audio detection relies on hand-crafted features, which lose...
Existing fake audio detection systems perform well in in-domain testing,...
In this paper, we propose a novel self-distillation method for fake spee...
Knowledge distillation addresses the problem of transferring knowledge f...
AI-powered code assistants, such as Copilot, are quickly becoming a
ubiq...
Developing models that can automatically generate detailed code explanat...
Code generation models can benefit data scientists' productivity by
auto...
Previous databases have been designed to further the development of fake...
There are already some datasets used for fake audio detection, such as t...
We propose a new technique based on program synthesis for automatically
...
Many effective attempts have been made for deepfake audio detection. How...
Many effective attempts have been made for fake audio detection. However...
The existing fake audio detection systems often rely on expert experienc...
Pre-trained large language models (LLMs) such as OpenAI Codex have shown...
Fake audio detection is a growing concern and some relevant datasets hav...
Large language models (LLMs) have demonstrated an impressive ability to
...
Program synthesis aims to generate executable programs that are consiste...
Analytical SQL is widely used in modern database applications and data
a...
Lung cancer has the highest mortality rate of deadly cancers in the worl...
Audio deepfake detection is an emerging topic, which was included in the...
This paper describes NiuTrans neural machine translation systems of the ...
This paper describes the submissions of the NiuTrans Team to the WNGT 20...
This paper describes the NiuTrans system for the WMT21 translation effic...
This paper addresses the efficiency challenge of Neural Architecture Sea...
Fake audio attack becomes a major threat to the speaker verification sys...
Diverse promising datasets have been designed to hold back the developme...
In this work, we present a memory-efficient fully convolutional network ...
Although exploring alternatives is fundamental to creating better interf...
This paper considers the problem of efficient exploration of unseen
envi...
This paper presents a new approach for precisely estimating the renal
va...
Models such as Sequence-to-Sequence and Image-to-Sequence are widely use...
We consider the problem of neural semantic parsing, which translates nat...
We present a neural semantic parser that translatesnatural language ques...
In conventional supervised training, a model is trained to fit all the
t...
We present new data and semantic parsing methods for the problem of mapp...