Zobrazeno 1 - 10
of 109
pro vyhledávání: '"Li, Shuai"'
Autor:
Liu, Xutong, Wang, Siwei, Zuo, Jinhang, Zhong, Han, Wang, Xuchuang, Wang, Zhiyong, Li, Shuai, Hajiesmaili, Mohammad, Lui, John C. S., Chen, Wei
We introduce a novel framework of combinatorial multi-armed bandits (CMAB) with multivariant and probabilistically triggering arms (CMAB-MT), where the outcome of each arm is a $d$-dimensional multivariant random variable and the feedback follows a g
Externí odkaz:
http://arxiv.org/abs/2406.01386
Large Language Models (LLMs) have shown propensity to generate hallucinated outputs, i.e., texts that are factually incorrect or unsupported. Existing methods for alleviating hallucinations typically require costly human annotations to identify and c
Externí odkaz:
http://arxiv.org/abs/2404.01588
Autor:
Zhang, Beibei, Xiang, Tian, Mao, Chentao, Zheng, Yuhua, Li, Shuai, Niu, Haoyi, Xi, Xiangming, Bai, Wenyuan, Gao, Feng
Time-jerk optimal trajectory planning is crucial in advancing robotic arms' performance in dynamic tasks. Traditional methods rely on solving complex nonlinear programming problems, bringing significant delays in generating optimized trajectories. In
Externí odkaz:
http://arxiv.org/abs/2403.17353
Web-based applications such as chatbots, search engines and news recommendations continue to grow in scale and complexity with the recent surge in the adoption of LLMs. Online model selection has thus garnered increasing attention due to the need to
Externí odkaz:
http://arxiv.org/abs/2403.07213
Remarkable successes were made in Medical Image Classification (MIC) recently, mainly due to wide applications of convolutional neural networks (CNNs). However, adversarial examples (AEs) exhibited imperceptible similarity with raw data, raising seri
Externí odkaz:
http://arxiv.org/abs/2403.06798
Deep neural networks were significantly vulnerable to adversarial examples manipulated by malicious tiny perturbations. Although most conventional adversarial attacks ensured the visual imperceptibility between adversarial examples and corresponding
Externí odkaz:
http://arxiv.org/abs/2402.03095
Large pretrained multilingual language models (ML-LMs) have shown remarkable capabilities of zero-shot cross-lingual transfer, without direct cross-lingual supervision. While these results are promising, follow-up works found that, within the multili
Externí odkaz:
http://arxiv.org/abs/2401.05792
Self-supervised learning (SSL) has empirically shown its data representation learnability in many downstream tasks. There are only a few theoretical works on data representation learnability, and many of those focus on final data representation, trea
Externí odkaz:
http://arxiv.org/abs/2401.03214
Autor:
Kong, Fang, Li, Shuai
Two-sided matching markets have been widely studied in the literature due to their rich applications. Since participants are usually uncertain about their preferences, online algorithms have recently been adopted to learn them through iterative inter
Externí odkaz:
http://arxiv.org/abs/2401.01528
In this work, we study the low-rank MDPs with adversarially changed losses in the full-information feedback setting. In particular, the unknown transition probability kernel admits a low-rank matrix decomposition \citep{REPUCB22}, and the loss functi
Externí odkaz:
http://arxiv.org/abs/2311.07876