Zobrazeno 1 - 10
of 8 372
pro vyhledávání: '"An, Xiaokai"'
Autor:
Li, Wenbin, Yao, Di, Gong, Chang, Chu, Xiaokai, Jing, Quanliang, Zhou, Xiaolei, Zhang, Yuxuan, Fan, Yunxia, Bi, Jingping
Trajectory anomaly detection, aiming to estimate the anomaly risk of trajectories given the Source-Destination (SD) pairs, has become a critical problem for many real-world applications. Existing solutions directly train a generative model for observ
Externí odkaz:
http://arxiv.org/abs/2412.18820
Autor:
Zheng, Lianqing, Yang, Long, Lin, Qunshu, Ai, Wenjin, Liu, Minghao, Lu, Shouyi, Liu, Jianan, Ren, Hongze, Mo, Jingyue, Bai, Xiaokai, Bai, Jie, Ma, Zhixiong, Zhu, Xichan
The rapid advancement of deep learning has intensified the need for comprehensive data for use by autonomous driving algorithms. High-quality datasets are crucial for the development of effective data-driven autonomous driving solutions. Next-generat
Externí odkaz:
http://arxiv.org/abs/2412.10734
We study decentralized multiagent optimization over networks, modeled as undirected graphs. The optimization problem consists of minimizing a nonconvex smooth function plus a convex extended-value function, which enforces constraints or extra structu
Externí odkaz:
http://arxiv.org/abs/2412.09556
Autor:
Wang, Xiaoyu, Xi, Ningyuan, Chen, Teng, Gu, Qingqing, Zhao, Yue, Chen, Xiaokai, Jiang, Zhonglin, Chen, Yong, Ji, Luo
Large Language Models (LLM) are usually fine-tuned to participate in dyadic or two-party dialogues, which can not adapt well to multi-party dialogues (MPD), which hinders their applications in such scenarios including multi-personal meetings, discuss
Externí odkaz:
http://arxiv.org/abs/2412.05342
Autor:
Yoon, Se-eun, Wei, Xiaokai, Jiang, Yexi, Pareek, Rachit, Ong, Frank, Gao, Kevin, McAuley, Julian, Gong, Michelle
In this paper, we present a systematic effort to design, evaluate, and implement a realistic conversational recommender system (CRS). The objective of our system is to allow users to input free-form text to request recommendations, and then receive a
Externí odkaz:
http://arxiv.org/abs/2411.19352
With the development of the internet, recommending interesting products to users has become a highly valuable research topic for businesses. Recommendation systems play a crucial role in addressing this issue. To prevent the leakage of each user's (c
Externí odkaz:
http://arxiv.org/abs/2411.18653
Vision is one of the essential sources through which humans acquire information. In this paper, we establish a novel framework for measuring image information content to evaluate the variation in information content during image transformations. With
Externí odkaz:
http://arxiv.org/abs/2411.16207
Autor:
Zhang, Zhi, Padilla, Carlos Misael Madrid, Luo, Xiaokai, Wang, Daren, Padilla, Oscar Hernan Madrid
In this paper, we focus on fully connected deep neural networks utilizing the Rectified Linear Unit (ReLU) activation function for nonparametric estimation. We derive non-asymptotic bounds that lead to convergence rates, addressing both temporal and
Externí odkaz:
http://arxiv.org/abs/2411.09961
The transverse-traceless gauge condition is an important concept in the theory of gravitational wave. It is well known that vacuum is one of the key conditions to guarantee the existence of the transverse-traceless gauge. Although it is thin, interst
Externí odkaz:
http://arxiv.org/abs/2410.04388
Autor:
Zhang, Zeren, Cheng, Jo-Ku, Deng, Jingyang, Tian, Lu, Ma, Jinwen, Qin, Ziran, Zhang, Xiaokai, Zhu, Na, Leng, Tuo
Mathematical reasoning remains an ongoing challenge for AI models, especially for geometry problems that require both linguistic and visual signals. As the vision encoders of most MLLMs are trained on natural scenes, they often struggle to understand
Externí odkaz:
http://arxiv.org/abs/2409.04214