activity
20122024
most citedCharacter-level Convolutional Network for Text Classification Applied to Chinese Corpus

18 citations · 47 across the 16 of their papers we have counts for

collaborators
Showing 2023Show all

6 papers · 1 filter

cs.CL2023

Well Begun is Half Done: Generator-agnostic Knowledge Pre-Selection for Knowledge-Grounded Dialogue

Lang Qin, Yao Zhang, Hongru Liang +2

Accurate knowledge selection is critical in knowledge-grounded dialogue systems. Towards a closer look at it, we offer a novel perspective to organize existing literature, i.e., kn…

eess.IV20235 cited

FusionU-Net: U-Net with Enhanced Skip Connection for Pathology Image Segmentation

Zongyi Li, Hongbing Lyu, Jun Wang

In recent years, U-Net and its variants have been widely used in pathology image segmentation tasks. One of the key designs of U-Net is the use of skip connections between the enco…

cs.CL20232 cited

How Do Large Language Models Capture the Ever-changing World Knowledge? A Review of Recent Advances

Zihan Zhang, Meng Fang, Ling Chen +2

Although large language models (LLMs) are impressive in solving various tasks, they can quickly be outdated after deployment. Maintaining their up-to-date status is a pressing conc…

cs.CV20233 cited

Can Prompt Learning Benefit Radiology Report Generation?

Jun Wang, Lixing Zhu, Abhir Bhalerao +1

Radiology report generation aims to automatically provide clinically meaningful descriptions of radiology images such as MRI and X-ray. Although great success has been achieved in…

cs.LG20231 cited

Large language models improve Alzheimer's disease diagnosis using multi-modality data

Yingjie Feng, Jun Wang, Xianfeng Gu +2

In diagnosing challenging conditions such as Alzheimer's disease (AD), imaging is an important reference. Non-imaging patient data such as patient information, genetic data, medica…

cs.CV2023

Open Set Classification of GAN-based Image Manipulations via a ViT-based Hybrid Architecture

Jun Wang, Omran Alamayreh, Benedetta Tondi +1

Classification of AI-manipulated content is receiving great attention, for distinguishing different types of manipulations. Most of the methods developed so far fail in the open-se…