Masked image modeling (MIM) has become a prevalent pre-training setup fo...
We propose a new neural network design paradigm Reversible Column Networ...
We have developed an end-to-end, retrosynthesis system, named ChemiRise,...
Vision Transformer (ViT) attains state-of-the-art performance in visual
...
Molecular modeling is an important topic in drug discovery. Decades of
r...
Temporal receptive fields of models play an important role in action
seg...
Label smoothing is an effective regularization tool for deep neural netw...
Emergent hardwares can support mixed precision CNN models inference that...
Convolutional neural networks (CNNs) are typically over-parameterized,
b...
With the rapid development of quantum key distribution (QKD) technology,...
In this paper, we put forward a simple yet effective method to detect
me...
Due to the intrinsic point-to-point feature of quantum key distribution
...
With the rise of crowdsourcing and mobile crowdsensing techniques, a lar...
With the development of mobile social networks, more and more crowdsourc...
Low-bit quantization is challenging to maintain high performance with li...
As the Quantum Key Distribution (QKD) technology supporting the pointto-...
In recent years, bike-sharing systems have been deployed in many cities,...