Zobrazeno 1 - 10
of 6 246
pro vyhledávání: '"Zhang, Zhang"'
Autor:
Li, Shilong, Bai, Ge, Zhang, Zhang, Liu, Ying, Lu, Chenji, Guo, Daichi, Liu, Ruifang, Sun, Yong
Predicting unseen relations that cannot be observed during the training phase is a challenging task in relation extraction. Previous works have made progress by matching the semantics between input instances and label descriptions. However, fine-grai
Externí odkaz:
http://arxiv.org/abs/2406.11429
Seeing clearly with high resolution is a foundation of Large Multimodal Models (LMMs), which has been proven to be vital for visual perception and reasoning. Existing works usually employ a straightforward resolution upscaling method, where the image
Externí odkaz:
http://arxiv.org/abs/2406.08487
Autor:
Tan, Jiayao, Lyu, Fan, Ni, Chenggong, Feng, Tingliang, Hu, Fuyuan, Zhang, Zhang, Zhao, Shaochuang, Wang, Liang
Continual Test-Time Adaptation (CTTA) aims to adapt a pre-trained model to a sequence of target domains during the test phase without accessing the source data. To adapt to unlabeled data from unknown domains, existing methods rely on constructing ps
Externí odkaz:
http://arxiv.org/abs/2406.02609
Autor:
Shi, Ziqi, Lyu, Fan, Liu, Ye, Shang, Fanhua, Hu, Fuyuan, Feng, Wei, Zhang, Zhang, Wang, Liang
Continual Test-Time Adaptation (CTTA) is an emerging and challenging task where a model trained in a source domain must adapt to continuously changing conditions during testing, without access to the original source data. CTTA is prone to error accum
Externí odkaz:
http://arxiv.org/abs/2405.14602
Autor:
Lyu, Fan, Liu, Daofeng, Zhao, Linglan, Zhang, Zhang, Shang, Fanhua, Hu, Fuyuan, Feng, Wei, Wang, Liang
Online Continual Learning (OCL) empowers machine learning models to acquire new knowledge online across a sequence of tasks. However, OCL faces a significant challenge: catastrophic forgetting, wherein the model learned in previous tasks is substanti
Externí odkaz:
http://arxiv.org/abs/2405.09133
Autor:
Zhang, YiFan, Chen, Weiqi, Zhu, Zhaoyang, Qin, Dalin, Sun, Liang, Wang, Xue, Wen, Qingsong, Zhang, Zhang, Wang, Liang, Jin, Rong
Online updating of time series forecasting models aims to tackle the challenge of concept drifting by adjusting forecasting models based on streaming data. While numerous algorithms have been developed, most of them focus on model design and updating
Externí odkaz:
http://arxiv.org/abs/2403.14949
Autor:
Zhang, Yi-Fan, Yu, Weichen, Wen, Qingsong, Wang, Xue, Zhang, Zhang, Wang, Liang, Jin, Rong, Tan, Tieniu
In the realms of computer vision and natural language processing, Large Vision-Language Models (LVLMs) have become indispensable tools, proficient in generating textual descriptions based on visual inputs. Despite their advancements, our investigatio
Externí odkaz:
http://arxiv.org/abs/2403.05262
Autor:
Jiang, Ziheng, Lin, Haibin, Zhong, Yinmin, Huang, Qi, Chen, Yangrui, Zhang, Zhi, Peng, Yanghua, Li, Xiang, Xie, Cong, Nong, Shibiao, Jia, Yulu, He, Sun, Chen, Hongmin, Bai, Zhihao, Hou, Qi, Yan, Shipeng, Zhou, Ding, Sheng, Yiyao, Jiang, Zhuo, Xu, Haohan, Wei, Haoran, Zhang, Zhang, Nie, Pengfei, Zou, Leqi, Zhao, Sida, Xiang, Liang, Liu, Zherui, Li, Zhe, Jia, Xiaoying, Ye, Jianxi, Jin, Xin, Liu, Xin
We present the design, implementation and engineering experience in building and deploying MegaScale, a production system for training large language models (LLMs) at the scale of more than 10,000 GPUs. Training LLMs at this scale brings unprecedente
Externí odkaz:
http://arxiv.org/abs/2402.15627
The prior drift is crucial in Continual Test-Time Adaptation (CTTA) methods that only use unlabeled test data, as it can cause significant error propagation. In this paper, we introduce VCoTTA, a variational Bayesian approach to measure uncertainties
Externí odkaz:
http://arxiv.org/abs/2402.08182
Autor:
Yang, Kang, Mao, Xinjun, Wang, Shangwen, Zhang, Tanghaoran, Lin, Bo, Wang, Yanlin, Qin, Yihao, Zhang, Zhang, Mao, Xiaoguang
Pre-trained code models have emerged as crucial tools in various code intelligence tasks. However, their effectiveness depends on the quality of the pre-training dataset, particularly the human reference comments, which serve as a bridge between the
Externí odkaz:
http://arxiv.org/abs/2312.15202