ShifCon: Enhancing Non-Dominant Language Capabilities with a Shift-based Contrastive Framework

Autor: Zhang, Hengyuan, Shang, Chenming, Wang, Sizhe, Zhang, Dongdong, Sun, Renliang, Yu, Yiyao, Yang, Yujiu, Wei, Furu

Although fine-tuning Large Language Models (LLMs) with multilingual data can rapidly enhance the multilingual capabilities of LLMs, they still exhibit a performance gap between the dominant language (e.g., English) and non-dominant ones due to the im

Externí odkaz: http://arxiv.org/abs/2410.19453

Understanding Multimodal Deep Neural Networks: A Concept Selection View

Autor: Shang, Chenming, Zhang, Hengyuan, Wen, Hao, Yang, Yujiu

The multimodal deep neural networks, represented by CLIP, have generated rich downstream applications owing to their excellent performance, thus making understanding the decision-making process of CLIP an essential research topic. Due to the complex

Externí odkaz: http://arxiv.org/abs/2404.08964

Improving Low-Resource Knowledge Tracing Tasks by Supervised Pre-training and Importance Mechanism Fine-tuning

Autor: Zhang, Hengyuan, Liu, Zitao, Huang, Shuyan, Shang, Chenming, Zhan, Bojun, Jiang, Yong

Knowledge tracing (KT) aims to estimate student's knowledge mastery based on their historical interactions. Recently, the deep learning based KT (DLKT) approaches have achieved impressive performance in the KT task. These DLKT models heavily rely on

Externí odkaz: http://arxiv.org/abs/2403.06725

NTIRE 2020 Challenge on Perceptual Extreme Super-Resolution: Methods and Results

Autor: Zhang, Kai, Gu, Shuhang, Timofte, Radu, Shang, Taizhang, Dai, Qiuju, Zhu, Shengchen, Yang, Tong, Guo, Yandong, Jo, Younghyun, Yang, Sejong, Kim, Seon Joo, Zha, Lin, Jiang, Jiande, Gao, Xinbo, Lu, Wen, Liu, Jing, Yoon, Kwangjin, Jeon, Taegyun, Akita, Kazutoshi, Ooba, Takeru, Ukita, Norimichi, Luo, Zhipeng, Yao, Yuehan, Xu, Zhenyu, He, Dongliang, Wu, Wenhao, Ding, Yukang, Li, Chao, Li, Fu, Wen, Shilei, Li, Jianwei, Yang, Fuzhi, Yang, Huan, Fu, Jianlong, Kim, Byung-Hoon, Baek, JaeHyun, Ye, Jong Chul, Fan, Yuchen, Huang, Thomas S., Lee, Junyeop, Lee, Bokyeung, Min, Jungki, Kim, Gwantae, Lee, Kanghyu, Park, Jaihyun, Mykhailych, Mykola, Zhong, Haoyu, Shi, Yukai, Yang, Xiaojun, Yang, Zhijing, Lin, Liang, Zhao, Tongtong, Peng, Jinjia, Wang, Huibing, Jin, Zhi, Wu, Jiahao, Chen, Yifu, Shang, Chenming, Zhang, Huanrong, Min, Jeongki, S, Hrishikesh P, Puthussery, Densen, C V, Jiji

This paper reviews the NTIRE 2020 challenge on perceptual extreme super-resolution with focus on proposed solutions and results. The challenge task was to super-resolve an input image with a magnification factor 16 based on a set of prior examples of

Externí odkaz: http://arxiv.org/abs/2005.01056