Wei Yuan
YOU?
Author Swipe
View article: Antithetic Noise in Diffusion Models
Antithetic Noise in Diffusion Models Open
We initiate a systematic study of antithetic initial noise in diffusion models. Across unconditional models trained on diverse datasets, text-conditioned latent-diffusion models, and diffusion-posterior samplers, we find that pairing each …
View article: Billet Number Recognition Based on Test-Time Adaptation
Billet Number Recognition Based on Test-Time Adaptation Open
During the steel billet production process, it is essential to recognize machine-printed or manually written billet numbers on moving billets in real-time. To address the issue of low recognition accuracy for existing scene text recognitio…
View article: CCS: Controllable and Constrained Sampling with Diffusion Models via Initial Noise Perturbation
CCS: Controllable and Constrained Sampling with Diffusion Models via Initial Noise Perturbation Open
Diffusion models have emerged as powerful tools for generative tasks, producing high-quality outputs across diverse domains. However, how the generated data responds to the initial noise perturbation in diffusion models remains under-explo…
View article: The Relationship between Social Support and Happiness: The Moderating Effect of Marital Status
The Relationship between Social Support and Happiness: The Moderating Effect of Marital Status Open
Study explores social support-well-being interplay, assessing marital status's moderation. 1000 adults in diverse marital states surveyed via questionnaires. Scales measured social support & well-being. Analysis showed strong positive link…
View article: KGA: A General Machine Unlearning Framework Based on Knowledge Gap Alignment
KGA: A General Machine Unlearning Framework Based on Knowledge Gap Alignment Open
Recent legislation of the "right to be forgotten" has led to the interest in machine unlearning, where the learned models are endowed with the function to forget information about specific training instances as if they have never existed i…
View article: Recent Advances in Concept Drift Adaptation Methods for Deep Learning
Recent Advances in Concept Drift Adaptation Methods for Deep Learning Open
In the ``Big Data'' age, the amount and distribution of data have increased wildly and changed over time in various time-series-based tasks, e.g weather prediction, network intrusion detection. However, deep learning models may become outd…
View article: Unified Question Generation with Continual Lifelong Learning
Unified Question Generation with Continual Lifelong Learning Open
Question Generation (QG), as a challenging Natural Language Processing task,\naims at generating questions based on given answers and context. Existing QG\nmethods mainly focus on building or training models for specific QG datasets.\nThes…
View article: Improving Neural Question Generation using Deep Linguistic Representation
Improving Neural Question Generation using Deep Linguistic Representation Open
Question Generation (QG) is a challenging Natural Language Processing (NLP) task which aims at generating questions with given answers and context. There are many works incorporating linguistic features to improve the performance of QG. Ho…
View article: Robust Android Malware Detection against Adversarial Example Attacks
Robust Android Malware Detection against Adversarial Example Attacks Open
Adversarial examples pose severe threats to Android malware detection because they can render the machine learning based detection systems useless. How to effectively detect Android malware under various adversarial example attacks becomes…
View article: Multi-view Common Component Discriminant Analysis for Cross-view Classification
Multi-view Common Component Discriminant Analysis for Cross-view Classification Open
Cross-view classification that means to classify samples from heterogeneous views is a significant yet challenging problem in computer vision. A promising approach to handle this problem is the multi-view subspace learning (MvSL), which in…
View article: Competitive Charging Station Pricing for Plug-in Electric Vehicles
Competitive Charging Station Pricing for Plug-in Electric Vehicles Open
This paper considers the problem of charging station pricing and plug-in electric vehicles (PEVs) station selection. When a PEV needs to be charged, it selects a charging station by considering the charging prices, waiting times, and trave…
View article: Learning-based Hand Gesture Sensing and Controlling Techniques for Automotive Electronics
Learning-based Hand Gesture Sensing and Controlling Techniques for Automotive Electronics Open
The control interfaces of current automotive electronics are mostly designed in push-button or touch panel styles. In order to decrease the eyes-off-the-road time and increase the driving safety, a novel hand gesture sensing and controllin…