With the development of blockchain technology, smart contracts have beco...
We present FIT: a transformer-based architecture with efficient
self-att...
Millions of smart contracts have been deployed onto Ethereum for providi...
Rain-by-snow weather removal is a specialized task in weather-degraded i...
We empirically study the effect of noise scheduling strategies for denoi...
The non-fungible token (NFT) is an emergent type of cryptocurrency that ...
We present the Recurrent Interface Network (RIN), a neural net architect...
Failure is common in clinical trials since the successful failures prese...
Visual anomaly detection, an important problem in computer vision, is us...
In the past few years, several attacks against the vulnerabilities of EO...
Panoptic segmentation assigns semantic and instance ID labels to every p...
We present Bit Diffusion: a simple and generic approach for generating
d...
Time series anomaly detection (TSAD) is an important data mining task wi...
Recent algorithms designed for reinforcement learning tasks focus on fin...
While language tasks are naturally expressed in a single, unified, model...
For those seeking healthcare advice online, AI based dialogue agents cap...
Semantic segmentation labels are expensive and time consuming to acquire...
Recent progress in Medical Artificial Intelligence (AI) has delivered sy...
Greybox fuzzing has been widely used in stateless programs and has achie...
Relative radiometric normalization(RRN) of different satellite images of...
Contrastive learning approaches have achieved great success in learning
...
We investigate the robustness of vision transformers (ViTs) through the ...
Deep reinforcement learning (DRL) has achieved super-human performance o...
Circuit routing has been a historically challenging problem in designing...
This paper presents Pix2Seq, a simple and generic framework for object
d...
Both image-caption pairs and translation pairs provide the means to lear...
This paper presents iBatch, a middleware system running on top of an
ope...
Attention-based models, exemplified by the Transformer, can effectively ...
Although hierarchical structures are popular in recent vision transforme...
Ethereum holds multiple billions of U.S. dollars in the form of Ether
cr...
Learning to predict the long-term future of video frames is notoriously
...
Self-supervised pretraining followed by supervised fine-tuning has seen
...
As the most popular blockchain that supports smart contracts, there are
...
Automatic self-diagnosis provides low-cost and accessible healthcare via...
Contrastive loss and its variants have become very popular recently for
...
It is common to use the softmax cross-entropy loss to train neural netwo...
Recent work has shown that, when integrated with adversarial training,
s...
Generalizable, transferrable, and robust representation learning on
grap...
Smart contracts are Turing-complete programs running on the blockchain. ...
Being the most popular permissionless blockchain that supports smart
con...
More than eight million smart contracts have been deployed into Ethereum...
One paradigm for learning from few labeled examples while making best us...
Data augmentations have been widely studied to improve the accuracy and
...
This paper presents SimCLR: a simple framework for contrastive learning ...
As deep neural networks (DNNs) achieve tremendous success across many
ap...
Embedding layer is commonly used to map discrete symbols into continuous...
Existing approaches for learning word embeddings often assume there are
...
Graph neural networks (GNNs) are shown to be successful in modeling
appl...
Most conventional heterogeneous network selection strategies applied in
...
Graph Neural Nets (GNNs) have received increasing attentions, partially ...