Zobrazeno 1 - 10
of 254
pro vyhledávání: '"Li HaoChuan"'
Autor:
Qu, Leigang, Li, Haochuan, Wang, Wenjie, Liu, Xiang, Li, Juncheng, Nie, Liqiang, Chua, Tat-Seng
Large Multimodal Models (LMMs) have demonstrated impressive capabilities in multimodal understanding and generation, pushing forward advancements in text-to-image generation. However, achieving accurate text-image alignment for LMMs, particularly in
Externí odkaz:
http://arxiv.org/abs/2412.05818
Autor:
Cheng, Yujie, Li, Xiaoting, Feng, Lantian, Li, Haochuan, Sun, Wenzhao, Song, Xinyu, Ding, Yuyang, Guo, Guangcan, Wang, Cheng, Ren, Xifeng
Periodically poled thin-film lithium niobate (TFLN) waveguides, which enable efficient quadratic nonlinear processes, serve as crucial foundation for classical and quantum signal processing. To expand their application scope, we provide the first inv
Externí odkaz:
http://arxiv.org/abs/2408.05907
How humans can efficiently and effectively acquire images has always been a perennial question. A typical solution is text-to-image retrieval from an existing database given the text query; however, the limited database typically lacks creativity. By
Externí odkaz:
http://arxiv.org/abs/2406.05814
Autor:
Li, Xiaoting, Li, Haochuan, Wang, Zhenzheng, Chen, Zhaoxi, Ma, Fei, Zhang, Ke, Sun, Wenzhao, Wang, Cheng
Thin-film periodically poled lithium niobate (TF-PPLN) devices have recently gained prominence for efficient wavelength conversion processes in both classical and quantum applications. However, the patterning and poling of TF-PPLN devices today are m
Externí odkaz:
http://arxiv.org/abs/2312.09568
Autor:
Zhao, Jie, Li, Xiaoting, Hu, Ting-Chen, Sayem, Ayed Al, Li, Haochuan, Tate, Al, Kim, Kwangwoong, Kopf, Rose, Sanjari, Pouria, Earnshaw, Mark, Fontaine, Nicolas K., Wang, Cheng, Blanco-Redondo, Andrea
Thin-film lithium niobate (TFLN) based frequency doublers have been widely recognized as essential components for both classical and quantum optical communications. Nonetheless, the efficiency of these devices is hindered by imperfections present in
Externí odkaz:
http://arxiv.org/abs/2307.06619
Classical analysis of convex and non-convex optimization methods often requires the Lipshitzness of the gradient, which limits the analysis to functions bounded by quadratics. Recent work relaxed this requirement to a non-uniform smoothness condition
Externí odkaz:
http://arxiv.org/abs/2306.01264
In this paper, we provide a rigorous proof of convergence of the Adaptive Moment Estimate (Adam) algorithm for a wide class of optimization objectives. Despite the popularity and efficiency of the Adam algorithm in training deep neural networks, its
Externí odkaz:
http://arxiv.org/abs/2304.13972
Gradient clipping is a standard training technique used in deep learning applications such as large-scale language modeling to mitigate exploding gradients. Recent experimental studies have demonstrated a fairly special behavior in the smoothness of
Externí odkaz:
http://arxiv.org/abs/2303.00883
Autor:
Zhang, Guoyong1 (AUTHOR) zhanggy@creei.cn, Li, Haochuan2 (AUTHOR) lihaochuan@hust.edu.cn, Wang, Lingli1 (AUTHOR), Wang, Weiying1 (AUTHOR), Guo, Jun2 (AUTHOR) hqin@hust.edu.cn, Qin, Hui2 (AUTHOR) xiu_ni@hust.edu.cn, Ni, Xiu2 (AUTHOR)
Publikováno v:
Energies (19961073). Nov2024, Vol. 17 Issue 22, p5707. 22p.
Despite the established convergence theory of Optimistic Gradient Descent Ascent (OGDA) and Extragradient (EG) methods for the convex-concave minimax problems, little is known about the theoretical guarantees of these methods in nonconvex settings. T
Externí odkaz:
http://arxiv.org/abs/2210.09382