no code implementations • 1 Nov 2024 • Yun Jiang, Zilong Xie, Wei zhang, Yun Fang, Shuai Pan
Retrieval-augmented generation methods often neglect the quality of content retrieved from external knowledge bases, resulting in irrelevant information or potential misinformation that negatively affects the generation results of large language models.
no code implementations • 21 May 2024 • Xin Jin, Hongyu Zhu, Mounîm A. El Yacoubi, Haiyang Li, Hongchao Liao, Huafeng Qin, Yun Jiang
To enable CNNs to capture comprehensive feature representations from palm-vein images, we explored the effect of convolutional kernel size on the performance of palm-vein identification networks and designed LaKNet, a network leveraging large kernel convolution and gating mechanism.
2 code implementations • 19 Dec 2023 • Huafeng Qin, Xin Jin, Yun Jiang, Mounim A. El-Yacoubi, Xinbo Gao
In this paper, we propose AdAutomixup, an adversarial automatic mixup augmentation approach that generates challenging samples to train a robust classifier for image classification, by alternatively optimizing the classifier and the mixup sample generator.
no code implementations • Findings of the Association for Computational Linguistics 2020 • Jiazhao Li, Corey Lester, Xinyan Zhao, Yuting Ding, Yun Jiang, V. G. Vinod Vydiswaran
We propose a novel machine translation-based approach, PharmMT, to automatically and reliably simplify prescription directions into patient-friendly language, thereby significantly reducing pharmacist workload.
no code implementations • 23 Dec 2020 • Sven Fabian, Florian Goertz, Yun Jiang
We provide a comprehensive and up-to-date analysis of the prospects to realize Dark Matter (DM) in the Inert Doublet Model, while simultaneously enhancing the Electroweak Phase Transition (EWPhT) such as to allow for electroweak baryogenesis.
High Energy Physics - Phenomenology High Energy Physics - Experiment
no code implementations • 5 Apr 2020 • Mingrui Yang, Yun Jiang, Dan Ma, Bhairav B. Mehta, Mark A. Griswold
The in vivo T1, T2 maps generated from the GAN-MRF fingerprints are in good agreement with those generated from the Bloch simulated fingerprints, showing good performance and robustness of the proposed GAN-MRF model.
no code implementations • 11 Apr 2019 • Yun Jiang, Ning Tan, Tingting Peng, Hai Zhang
In the proposed D-Net, the dilation convolution is used in the backbone network to obtain a larger receptive field without losing spatial resolution, so as to reduce the loss of feature information and to reduce the difficulty of tiny thin vessels segmentation.
no code implementations • 11 May 2018 • Yun Jiang, Ning Tan
However, existing methods have various problems in the segmentation of the retinal vessels, such as insufficient segmentation of retinal vessels, weak anti-noise interference ability, and sensitivity to lesions, etc.
no code implementations • 23 Oct 2017 • Bo Zhao, Justin P. Haldar, Congyu Liao, Dan Ma, Yun Jiang, Mark A. Griswold, Kawin Setsompop, Lawrence L. Wald
Magnetic resonance (MR) fingerprinting is a new quantitative imaging paradigm, which simultaneously acquires multiple MR tissue parameter maps in a single experiment.
Signal Processing
2 code implementations • 19 Sep 2017 • Ilaria Brivio, Yun Jiang, Michael Trott
We report codes for the Standard Model Effective Field Theory (SMEFT) in FeynRules -- the SMEFTsim package.
High Energy Physics - Phenomenology High Energy Physics - Experiment
no code implementations • CVPR 2013 • Yun Jiang, Hema Koppula, Ashutosh Saxena
Given only a dataset of scenes containing objects but not humans, we show that our algorithm can recover the human object relationships.