Výsledky vyhledávání

Report

Drawing the Line: Enhancing Trustworthiness of MLLMs Through the Power of Refusal

Autor: Wang, Yuhao, Zhu, Zhiyuan, Liu, Heyang, Liao, Yusheng, Liu, Hongcheng, Wang, Yanfeng, Wang, Yu

Multimodal large language models (MLLMs) excel at multimodal perception and understanding, yet their tendency to generate hallucinated or inaccurate responses undermines their trustworthiness. Existing methods have largely overlooked the importance o

Externí odkaz: http://arxiv.org/abs/2412.11196

Zobrazit plný text záznamu

Report

GTSinger: A Global Multi-Technique Singing Corpus with Realistic Music Scores for All Singing Tasks

Autor: Zhang, Yu, Pan, Changhao, Guo, Wenxiang, Li, Ruiqi, Zhu, Zhiyuan, Wang, Jialei, Xu, Wenhao, Lu, Jingyu, Hong, Zhiqing, Wang, Chuxin, Zhang, LiChao, He, Jinzheng, Jiang, Ziyue, Chen, Yuxin, Yang, Chen, Zhou, Jiecheng, Cheng, Xinyu, Zhao, Zhou

The scarcity of high-quality and multi-task singing datasets significantly hinders the development of diverse controllable and personalized singing tasks, as existing singing datasets suffer from low quality, limited diversity of languages and singer

Externí odkaz: http://arxiv.org/abs/2409.13832

Zobrazit plný text záznamu

Akademický článek

Application of the BOPPPS combined with CPBL and scenario simulation in cardiovascular internal medicine teaching

Autor: YOU Shuxin, ZHOU Xingyu, ZHU Zhiyuan, AN Chenhong, ZHOU Xianliang, LUO Fang

Publikováno v: Jichu yixue yu linchuang, Vol 44, Iss 12, Pp 1756-1760 (2024)

Objective This study aims to evaluate the application of BOPPPS teaching model combined with case and problem-based learning (CPBL) and the scenario simulation in cardiovascular internal medicine education. Methods The study included cardiovascular i

Externí odkaz: https://doaj.org/article/c563372873d9478caf90e088236e4795