Zobrazeno 1 - 10
of 21 155
pro vyhledávání: '"Zhang, zheng"'
Autor:
Ghiasvand, Sajjad, Yang, Yifan, Xue, Zhiyu, Alizadeh, Mahnoosh, Zhang, Zheng, Pedarsani, Ramtin
Parameter-efficient fine-tuning (PEFT) methods typically assume that Large Language Models (LLMs) are trained on data from a single device or client. However, real-world scenarios often require fine-tuning these models on private data distributed acr
Externí odkaz:
http://arxiv.org/abs/2410.13097
Autor:
Guo, Pinxue, Zhao, Zixu, Gao, Jianxiong, Wu, Chongruo, He, Tong, Zhang, Zheng, Xiao, Tianjun, Zhang, Wenqiang
Video segmentation is essential for advancing robotics and autonomous driving, particularly in open-world settings where continuous perception and object association across video frames are critical. While the Segment Anything Model (SAM) has excelle
Externí odkaz:
http://arxiv.org/abs/2410.08781
Autor:
Liu, Bang, Zhang, Li-Hua, Wang, Ya-Jun, Zhang, Jun, Wang, Qi-Feng, Ma, Yu, Han, Tian-Yu, Zhang, Zheng-Yuan, Shao, Shi-Yao, Li, Qing, Chen, Han-Chao, Nan, Jia-Dou, Zhu, Dong-Yang, Yin, Yi-Ming, Shi, Bao-Sen, Ding, Dong-Sheng
Higgs and Goldstone modes manifest as fluctuations in the order parameter of system, offering insights into its phase transitions and symmetry properties. Exploring the dynamics of these collective excitations in a Rydberg atoms system advances vario
Externí odkaz:
http://arxiv.org/abs/2410.06047
Autor:
Shi, Yijie, Wang, Xi, Wang, Zhong, Zhang, Zheng, Hua, Fuyong, Chen, Chao, Hu, Chunlong, Tang, Jiang, Liang, Wenxi
Antimony Selenide (Sb$_2$Se$_3$) is an attractive candidate of photovoltaics with not yet satisfying efficiency. Beside defects, polaron formation originated from lattice distortion was proposed to account for trapping free carriers, and the subseque
Externí odkaz:
http://arxiv.org/abs/2410.05155
Autor:
Jiayang, Cheng, Chan, Chunkit, Zhuang, Qianqian, Qiu, Lin, Zhang, Tianhang, Liu, Tengxiao, Song, Yangqiu, Zhang, Yue, Liu, Pengfei, Zhang, Zheng
The rise of large language models (LLMs) has significantly influenced the quality of information in decision-making systems, leading to the prevalence of AI-generated content and challenges in detecting misinformation and managing conflicting informa
Externí odkaz:
http://arxiv.org/abs/2410.04068
Autor:
Hu, Yuntong, Li, Zhuofeng, Zhang, Zheng, Ling, Chen, Kanjiani, Raasikh, Zhao, Boxin, Zhao, Liang
In this work, we present HiReview, a novel framework for hierarchical taxonomy-driven automatic literature review generation. With the exponential growth of academic documents, manual literature reviews have become increasingly labor-intensive and ti
Externí odkaz:
http://arxiv.org/abs/2410.03761
Publikováno v:
IEEE Transactions on Image Processing, vol. 33, pp. 2558-2571, 2024
Despite remarkable successes in unimodal learning tasks, backdoor attacks against cross-modal learning are still underexplored due to the limited generalization and inferior stealthiness when involving multiple modalities. Notably, since works in thi
Externí odkaz:
http://arxiv.org/abs/2410.02182
Supervised fine-tuning (SFT) is crucial for adapting Large Language Models (LLMs) to specific tasks. In this work, we demonstrate that the order of training data can lead to significant training imbalances, potentially resulting in performance degrad
Externí odkaz:
http://arxiv.org/abs/2410.03743
Autor:
Bull, Philip, El-Makadema, Ahmed, Garsden, Hugh, Edgley, John, Roddis, Neil, Chluba, Jens, Conselice, Christopher J., Dutta, Sohini, Glasscock, Katrine A., Nasirudin, Ainulnabilah, Norris, Jordan, Wilensky, Michael J., Ye, Isabelle, Zhang, Zheng
The sky-averaged brightness temperature of the 21cm line from neutral hydrogen provides a sensitive probe of the thermal state of the intergalactic medium, particularly before and during Cosmic Dawn and the Epoch of Reionisation. This `global signal'
Externí odkaz:
http://arxiv.org/abs/2410.00076
Autor:
Bai, Zechen, He, Tong, Mei, Haiyang, Wang, Pichao, Gao, Ziteng, Chen, Joya, Liu, Lei, Zhang, Zheng, Shou, Mike Zheng
We introduce VideoLISA, a video-based multimodal large language model designed to tackle the problem of language-instructed reasoning segmentation in videos. Leveraging the reasoning capabilities and world knowledge of large language models, and augm
Externí odkaz:
http://arxiv.org/abs/2409.19603