Zobrazeno 1 - 10
of 115 398
pro vyhledávání: '"A, Bei"'
Recent advancements in vision-language models have enhanced performance by increasing the length of visual tokens, making them much longer than text tokens and significantly raising computational costs. However, we observe that the visual tokens gene
Externí odkaz:
http://arxiv.org/abs/2412.04467
Autor:
Huang, Zhenglin, Hu, Jinwei, Li, Xiangtai, He, Yiwei, Zhao, Xingyu, Peng, Bei, Wu, Baoyuan, Huang, Xiaowei, Cheng, Guangliang
The rapid advancement of generative models in creating highly realistic images poses substantial risks for misinformation dissemination. For instance, a synthetic image, when shared on social media, can mislead extensive audiences and erode trust in
Externí odkaz:
http://arxiv.org/abs/2412.04292
Autor:
Shan, Weiqiao, Meng, Long, Zheng, Tong, Luo, Yingfeng, Li, Bei, Wang, junxin, Xiao, Tong, Zhu, Jingbo
Large language models (LLMs) exhibit exceptional performance across various downstream tasks. However, they encounter limitations due to slow inference speeds stemming from their extensive parameters. The early exit (EE) is an approach that aims to a
Externí odkaz:
http://arxiv.org/abs/2412.01455
Autor:
AI, 01., Wake, Alan, Wang, Albert, Chen, Bei, Lv, C. X., Li, Chao, Huang, Chengen, Cai, Chenglin, Zheng, Chujie, Cooper, Daniel, Dai, Ethan, Zhou, Fan, Hu, Feng, Ji, Heng, Qiu, Howard, Zhu, Jiangcheng, Tian, Jun, Su, Katherine, Zhang, Lihuan, Li, Liying, Song, Ming, Li, Mou, Liu, Peng, Hu, Qicheng, Wang, Shawn, Zhou, Shijun, Li, Shiyong, Zhu, Tianhang, Xie, Wen, He, Xiang, Chen, Xiaobo, Hu, Xiaohui, Ren, Xiaoyi, Niu, Xinyao, Li, Yanpeng, Zhao, Yongke, Luo, Yongzhen, Xu, Yuchi, Sha, Yuxuan, Yan, Zhaodong, Liu, Zhiyuan, Zhang, Zirui
This technical report presents Yi-Lightning, our latest flagship large language model (LLM). It achieves exceptional performance, ranking 6th overall on Chatbot Arena, with particularly strong results (2nd to 4th place) in specialized categories incl
Externí odkaz:
http://arxiv.org/abs/2412.01253
Autor:
Liu, Bei, Qian, Yanmin
Recent speaker verification (SV) systems have shown a trend toward adopting deeper speaker embedding extractors. Although deeper and larger neural networks can significantly improve performance, their substantial memory requirements hinder training o
Externí odkaz:
http://arxiv.org/abs/2412.01195
Autor:
Li, Shu-Yue, Zhang, Qing-Min, Ying, Bei-Li, Feng, Li, Su, Ying-Na, Zhang, Mu-Sheng Lin. Yan-Jie
In this paper, we perform a follow-up investigation of the solar eruption originating from active region (AR) 13575 on 2024 February 9. The primary eruption of a hot channel (HC) generates an X3.4 class flare, a full-halo coronal mass ejection (CME),
Externí odkaz:
http://arxiv.org/abs/2412.01123
Autor:
Li, Qixiu, Liang, Yaobo, Wang, Zeyu, Luo, Lin, Chen, Xi, Liao, Mozheng, Wei, Fangyun, Deng, Yu, Xu, Sicheng, Zhang, Yizhong, Wang, Xiaofan, Liu, Bei, Fu, Jianlong, Bao, Jianmin, Chen, Dong, Shi, Yuanchun, Yang, Jiaolong, Guo, Baining
The advancement of large Vision-Language-Action (VLA) models has significantly improved robotic manipulation in terms of language-guided task execution and generalization to unseen scenarios. While existing VLAs adapted from pretrained large Vision-L
Externí odkaz:
http://arxiv.org/abs/2411.19650
Autor:
Bei, Yuanchen, Chen, Weizhi, Chen, Hao, Zhou, Sheng, Yang, Carl, Fan, Jiapei, Huang, Longtao, Bu, Jiajun
Multi-label node classification is an important yet under-explored domain in graph mining as many real-world nodes belong to multiple categories rather than just a single one. Although a few efforts have been made by utilizing Graph Convolution Netwo
Externí odkaz:
http://arxiv.org/abs/2411.17350
Transformer-based large language models (LLMs) have achieved remarkable success as model sizes continue to grow, yet their deployment remains challenging due to significant computational and memory demands. Quantization has emerged as a promising sol
Externí odkaz:
http://arxiv.org/abs/2411.16158
Generative Pre-trained Transformers (GPTs) have demonstrated remarkable performance across diverse domains through the extensive scaling of model parameters. Recent works observe the redundancy across the transformer blocks and develop compression me
Externí odkaz:
http://arxiv.org/abs/2411.14507