In this study, Cu-Cr composites were studied by nanoindentation. Arrays ...
Co-speech gesture generation is crucial for automatic digital avatar
ani...
By integrating complementary information from RGB image and depth map, t...
Knowledge tracing (KT) aims to monitor students' evolving knowledge stat...
In modern dialogue systems, the use of Large Language Models (LLMs) has ...
Zero-shot text-to-speech aims at synthesizing voices with unseen speech
...
Deep neural networks (DNNs) are of critical use in different domains. To...
Graph data management is instrumental for several use cases such as
reco...
Passenger clustering based on travel records is essential for transporta...
The advent and fast development of neural networks have revolutionized t...
Modeling complex spatiotemporal dependencies in correlated traffic serie...
Scaling text-to-speech to a large and wild dataset has been proven to be...
We are interested in a novel task, namely low-resource text-to-talking
a...
In this paper, we consider the problem of Iterative Machine Teaching (IM...
This paper proposes to learn Multi-task, Multi-modal Direct Acyclic Grap...
In recent years, medical information technology has made it possible for...
The chest X-ray is often utilized for diagnosing common thoracic disease...
The multi-answer phenomenon, where a question may have multiple answers
...
Causal reasoning, the ability to identify cause-and-effect relationship,...
Large diffusion models have been successful in text-to-audio (T2A) synth...
Large Language Models (LLMs), like LLaMA, have exhibited remarkable
perf...
Finetuning pretrained language models (LMs) have enabled appealing
perfo...
Pretrained language models (LMs) have shown compelling performance on va...
While Current TTS systems perform well in synthesizing high-quality spee...
The chest X-ray (CXR) is one of the most common and easy-to-get medical ...
The chest X-ray (CXR) is commonly employed to diagnose thoracic illnesse...
Rehabilitation training for patients with motor disabilities usually req...
Real-time emotion-based music arrangement, which aims to transform a giv...
This paper presents our efforts to democratize ChatGPT across language. ...
Transformer-based large language models (LLMs) have achieved great succe...
New retrieval tasks have always been emerging, thus urging the developme...
Road extraction is a process of automatically generating road maps mainl...
Although many large-scale knowledge bases (KBs) claim to contain multili...
Chatbots are expected to be knowledgeable across multiple domains, e.g. ...
Artificial intelligence is to teach machines to take actions like humans...
The service quality ranking of airlines is a crucial factor for their
su...
Knowledge tracing aims to trace students' evolving knowledge states by
p...
While deep generative models have empowered music generation, it remains...
Recent model-based reference-free metrics for open-domain dialogue evalu...
Dialogue summarization is abstractive in nature, making it suffer from
f...
Prompt tuning learns soft prompts to condition frozen Pre-trained Langua...
In recent years, RGB-T salient object detection (SOD) has attracted
cont...
Recent advances in distilling pretrained language models have discovered...
Focusing on the issue of how to effectively capture and utilize
cross-mo...
Traditional machine learning methods have been widely studied in financi...
Output length is critical to dialogue summarization systems. The dialogu...
An activation function is an element-wise mathematical function and play...
Real-time music accompaniment generation has a wide range of application...
Multi-hop Knowledge Base Question Answering(KBQA) aims to find the answe...
Fully-supervised salient object detection (SOD) methods have made great
...