We introduce beta diffusion, a novel generative modeling method that
int...
Existing face forgery detection models try to discriminate fake images b...
Long-term time series forecasting plays an important role in various
rea...
We present Prompt Diffusion, a framework for enabling in-context learnin...
Small-scale automation services in Software Engineering, known as SE Bot...
Diffusion models are powerful, but they require a lot of time and data t...
Most urban applications necessitate building footprints in the form of
c...
Diffusion models have shown remarkable success in visual synthesis, but ...
Cellular traffic prediction is an indispensable part for intelligent
tel...
With increasing demands for flexible work models, many IT organizations ...
The safety of an automated vehicle hinges crucially upon the accuracy of...
The deep neural network (DNN) models are deemed confidential due to thei...
Offline reinforcement learning (RL), which aims to learn an optimal poli...
This paper proposes probabilistic conformal prediction (PCP), a predicti...
For stable training of generative adversarial networks (GANs), injecting...
In this dissertation, we propose a memory and computing coordinated
meth...
Topology impacts important network performance metrics, including link
u...
Color constancy aims to restore the constant colors of a scene under
dif...
Autonomous driving demands accurate perception and safe decision-making....
Offline reinforcement learning enables learning from a fixed dataset, wi...
In this paper, we present Uformer, an effective and efficient
Transforme...
The success of an open source software (OSS) project requires effective
...
Learning from imperfect data becomes an issue in many industrial applica...
To improve the sample efficiency of policy-gradient based reinforcement
...
Cutting-edge embedded system applications, such as self-driving cars and...
Integration of aerial and ground images has been proved as an efficient
...
Sequence generation models are commonly refined with reinforcement learn...
Thompson sampling is an efficient algorithm for sequential decision maki...
Open-source developers, particularly the elite developers, maintain a di...