Zobrazeno 1 - 10
of 33 410
pro vyhledávání: '"Xiaohua, P."'
Diffusion-based text-to-image models have shown immense potential for various image-related tasks. However, despite their prominence and popularity, customizing these models using unauthorized data also brings serious privacy and intellectual propert
Externí odkaz:
http://arxiv.org/abs/2412.18791
Artificial intelligence is fundamentally transforming financial investment decision-making paradigms, with deep reinforcement learning (DRL) demonstrating significant application potential in domains such as robo-advisory services. Given that traditi
Externí odkaz:
http://arxiv.org/abs/2412.18563
It is significantly challenging to recognize daily human actions in homes due to the diversity and dynamic changes in unconstrained home environments. It spurs the need to continually adapt to various users and scenes. Fine-tuning current video under
Externí odkaz:
http://arxiv.org/abs/2412.16946
Autor:
Qi, Zhengyang, Xu, Xiaohua
Flow-based generative models (FMs) have rapidly advanced as a method for mapping noise to data, its efficient training and sampling process makes it widely applicable in various fields. FMs can be viewed as a variant of diffusion models (DMs). At the
Externí odkaz:
http://arxiv.org/abs/2412.16512
Recommender systems have become increasingly influential in shaping user behavior and decision-making, highlighting their growing impact in various domains. Meanwhile, the widespread adoption of machine learning models in recommender systems has rais
Externí odkaz:
http://arxiv.org/abs/2412.12836
This paper is devoted to the time decay estimates for the following beam equation with a potential on the line: $$ \partial_t^2 u + \left( \Delta^2 + m^2 + V(x) \right) u = 0, \ \ u(0, x) = f(x),\quad \partial_t u(0, x) = g(x), $$ where $V$ is a real
Externí odkaz:
http://arxiv.org/abs/2412.09061
Autor:
Steiner, Andreas, Pinto, André Susano, Tschannen, Michael, Keysers, Daniel, Wang, Xiao, Bitton, Yonatan, Gritsenko, Alexey, Minderer, Matthias, Sherbondy, Anthony, Long, Shangbang, Qin, Siyang, Ingle, Reeve, Bugliarello, Emanuele, Kazemzadeh, Sahar, Mesnard, Thomas, Alabdulmohsin, Ibrahim, Beyer, Lucas, Zhai, Xiaohua
PaliGemma 2 is an upgrade of the PaliGemma open Vision-Language Model (VLM) based on the Gemma 2 family of language models. We combine the SigLIP-So400m vision encoder that was also used by PaliGemma with the whole range of Gemma 2 models, from the 2
Externí odkaz:
http://arxiv.org/abs/2412.03555
Autor:
Sun, Haowei, Hu, Jinwu, Zhang, Zhirui, Tian, Haoyuan, Xie, Xinze, Wang, Yufeng, Yu, Zhuliang, Xie, Xiaohua, Tan, Mingkui
Drone Visual Active Tracking aims to autonomously follow a target object by controlling the motion system based on visual observations, providing a more practical solution for effective tracking in dynamic environments. However, accurate Drone Visual
Externí odkaz:
http://arxiv.org/abs/2412.00744
3D Gaussian Splatting (3DGS) has recently created impressive assets for various applications. However, the copyright of these assets is not well protected as existing watermarking methods are not suited for 3DGS considering security, capacity, and in
Externí odkaz:
http://arxiv.org/abs/2411.19895
Beyond-diagonal reconfigurable intelligent surface (BD-RIS) has garnered significant research interest recently due to its ability to generalize existing reconfigurable intelligent surface (RIS) architectures and provide enhanced performance through
Externí odkaz:
http://arxiv.org/abs/2411.18480