Zobrazeno 1 - 10
of 125 264
pro vyhledávání: '"Wang,Yu"'
Autor:
Li, Shiyao, Hu, Yingchun, Ning, Xuefei, Liu, Xihui, Hong, Ke, Jia, Xiaotao, Li, Xiuhong, Yan, Yaqi, Ran, Pei, Dai, Guohao, Yan, Shengen, Yang, Huazhong, Wang, Yu
Vision-Language Models (VLMs) have enabled a variety of real-world applications. The large parameter size of VLMs brings large memory and computation overhead which poses significant challenges for deployment. Post-Training Quantization (PTQ) is an e
Externí odkaz:
http://arxiv.org/abs/2412.19509
In this paper, the mixed equilibrium problem with coupled inequality constraints in dynamic environments is solved by employing a multi-agent system, where each agent only has access to its own bifunction, its own constraint function, and can only co
Externí odkaz:
http://arxiv.org/abs/2412.19399
Autor:
Gu, Qiuyi, Ye, Zhaocheng, Yu, Jincheng, Tang, Jiahao, Yi, Tinghao, Dong, Yuhan, Wang, Jian, Cui, Jinqiang, Chen, Xinlei, Wang, Yu
Collaborative perception in unknown environments is crucial for multi-robot systems. With the emergence of foundation models, robots can now not only perceive geometric information but also achieve open-vocabulary scene understanding. However, existi
Externí odkaz:
http://arxiv.org/abs/2412.18381
In this article, we address the metrological problem of estimating collective stochastic properties of a many-body quantum system. Canonical examples include center-of-mass quadrature fluctuations in a system of bosonic modes and correlated dephasing
Externí odkaz:
http://arxiv.org/abs/2412.17903
Autoregressive (AR) models have achieved state-of-the-art performance in text and image generation but suffer from slow generation due to the token-by-token process. We ask an ambitious question: can a pre-trained AR model be adapted to generate outp
Externí odkaz:
http://arxiv.org/abs/2412.17153
Contrastive learning is a prevalent technique in self-supervised vision representation learning, typically generating positive pairs by applying two data augmentations to the same image. Designing effective data augmentation strategies is crucial for
Externí odkaz:
http://arxiv.org/abs/2412.16522
Autor:
Yuan, Zhihang, Shang, Yuzhang, Zhang, Hanling, Fang, Tongcheng, Xie, Rui, Xu, Bingxin, Yan, Yan, Yan, Shengen, Dai, Guohao, Wang, Yu
Recent advances in autoregressive (AR) models with continuous tokens for image generation show promising results by eliminating the need for discrete tokenization. However, these models face efficiency challenges due to their sequential token generat
Externí odkaz:
http://arxiv.org/abs/2412.14170