Zobrazeno 1 - 10
of 82
pro vyhledávání: '"Lu, Xinyang"'
Existing sample-based methods, like influence functions and representer points, measure the importance of a training point by approximating the effect of its removal from training. As such, they are skewed towards outliers and points that are very cl
Externí odkaz:
http://arxiv.org/abs/2408.05976
The rapid evolution of large language models (LLMs) represents a substantial leap forward in natural language understanding and generation. However, alongside these advancements come significant challenges related to the accountability and transparen
Externí odkaz:
http://arxiv.org/abs/2407.04981
With the widespread applications of neural networks (NNs) trained on personal data, machine unlearning has become increasingly important for enabling individuals to exercise their personal data ownership, particularly the "right to be forgotten" from
Externí odkaz:
http://arxiv.org/abs/2406.14507
Autor:
Wang, Jingtan, Lu, Xinyang, Zhao, Zitong, Dai, Zhongxiang, Foo, Chuan-Sheng, Ng, See-Kiong, Low, Bryan Kian Hsiang
The impressive performances of Large Language Models (LLMs) and their immense potential for commercialization have given rise to serious concerns over the Intellectual Property (IP) of their training data. In particular, the synthetic texts generated
Externí odkaz:
http://arxiv.org/abs/2310.00646
We study a two-dimensional quaternary inhibitory system. This free energy functional combines an interface energy favoring micro-domain growth with a Coulomb-type long range interaction energy which prevents micro-domains from unlimited spreading. He
Externí odkaz:
http://arxiv.org/abs/2307.12504
Action and Trajectory Planning for Urban Autonomous Driving with Hierarchical Reinforcement Learning
Reinforcement Learning (RL) has made promising progress in planning and decision-making for Autonomous Vehicles (AVs) in simple driving scenarios. However, existing RL algorithms for AVs fail to learn critical driving skills in complex urban scenario
Externí odkaz:
http://arxiv.org/abs/2306.15968
Empowering large language models to accurately express confidence in their answers is essential for trustworthy decision-making. Previous confidence elicitation methods, which primarily rely on white-box access to internal model information or model
Externí odkaz:
http://arxiv.org/abs/2306.13063
We consider a sharp-interface model of $ABC$ triblock copolymers, for which the surface tension $\sigma_{ij}$ across the interface separating phase $i$ from phase $j$ may depend on the components. We study global minimizers of the associated ternary
Externí odkaz:
http://arxiv.org/abs/2212.06381
Autor:
Lu, Xinyang, Slepcev, Dejan
We propose a model for finding one-dimensional structure in a given measure. Our approach is based on minimizing an objective functional which combines the average-distance functional to measure the quality of the approximation and penalizes the curv
Externí odkaz:
http://arxiv.org/abs/2012.14532
In this paper we study a gradient flow generated by the Landau-de Gennes free energy that describes nematic liquid crystal configurations in the space of $Q$-tensors. This free energy density functional is composed of three quadratic terms as the ela
Externí odkaz:
http://arxiv.org/abs/2011.09541