In the era of large-scale language models, the substantial parameter siz...
Multi-view 3D detection based on BEV (bird-eye-view) has recently achiev...
Subword tokenization is a key part of many NLP pipelines. However, littl...
Byte-Pair Encoding (BPE) is a popular algorithm used for tokenizing data...
Recently, there has been a growing interest in the development of
gradie...
To predict the next token, autoregressive models ordinarily examine the ...
Language modeling, a central task in natural language processing, involv...
Causal chain reasoning (CCR) is an essential ability for many decision-m...
Mixed-precision quantization has been widely applied on deep neural netw...
The complicated architecture and high training cost of vision transforme...
While transferring a pretrained language model, common approaches
conven...
Given a task, human learns from easy to hard, whereas the model learns
r...
Predicting the subsequent event for an existing event context is an impo...
Understanding causality has vital importance for various Natural Languag...
For binary neural networks (BNNs) to become the mainstream on-device com...
Existing deep convolutional neural networks (CNNs) generate massive
inte...
Understanding event and event-centered commonsense reasoning are crucial...
With the increasing size of Deep Neural Network (DNN) models, the high m...
An analog neural network computing engine based on CMOS-compatible
charg...
A memristive neural network computing engine based on CMOS-compatible
ch...
Deep convolutional neural networks (CNN) are widely used in modern artif...
Convolutional neural network (CNN) offers significant accuracy in image
...
AI applications have emerged in current world. Among AI applications,
co...
Neuromorphic vision processor is an electronic implementation of vision
...
Touch sensing, as a major human/machine interface, is widely used in var...