Zobrazeno 1 - 10
of 5 912
pro vyhledávání: '"An, Jiachun"'
Semi-supervised learning (SSL), exemplified by FixMatch (Sohn et al., 2020), has shown significant generalization advantages over supervised learning (SL), particularly in the context of deep neural networks (DNNs). However, it is still unclear, from
Externí odkaz:
http://arxiv.org/abs/2410.11206
Autor:
Li, Jiachun, Cao, Pengfei, Wang, Chenhao, Jin, Zhuoran, Chen, Yubo, Liu, Kang, Jiang, Xiaojian, Xu, Jiexin, Zhao, Jun
Large language models (LLMs) sometimes demonstrate poor performance on knowledge-intensive tasks, commonsense reasoning is one of them. Researchers typically address these issues by retrieving related knowledge from knowledge graphs or employing self
Externí odkaz:
http://arxiv.org/abs/2410.09541
Inductive reasoning is an essential capability for large language models (LLMs) to achieve higher intelligence, which requires the model to generalize rules from observed facts and then apply them to unseen examples. We present {\scshape Mirage}, a s
Externí odkaz:
http://arxiv.org/abs/2410.09542
Given n experiment subjects with potentially heterogeneous covariates and two possible treatments, namely active treatment and control, this paper addresses the fundamental question of determining the optimal accuracy in estimating the treatment effe
Externí odkaz:
http://arxiv.org/abs/2410.05552
Drawing on the intricate structures of the brain, Spiking Neural Networks (SNNs) emerge as a transformative development in artificial intelligence, closely emulating the complex dynamics of biological neural networks. While SNNs show promising effici
Externí odkaz:
http://arxiv.org/abs/2408.00280
Autor:
Jin, Zhuoran, Cao, Pengfei, Wang, Chenhao, He, Zhitao, Yuan, Hongbang, Li, Jiachun, Chen, Yubo, Liu, Kang, Zhao, Jun
Large language models (LLMs) inevitably memorize sensitive, copyrighted, and harmful knowledge from the training corpus; therefore, it is crucial to erase this knowledge from the models. Machine unlearning is a promising solution for efficiently remo
Externí odkaz:
http://arxiv.org/abs/2406.10890
Large language models (LLMs) suffer from serious unfaithful chain-of-thought (CoT) issues. Previous work attempts to measure and explain it but lacks in-depth analysis within CoTs and does not consider the interactions among all reasoning components
Externí odkaz:
http://arxiv.org/abs/2405.18915
We present Piecewise Rectified Flow (PeRFlow), a flow-based method for accelerating diffusion models. PeRFlow divides the sampling process of generative flows into several time windows and straightens the trajectories in each interval via the reflow
Externí odkaz:
http://arxiv.org/abs/2405.07510
Contextual bandit with linear reward functions is among one of the most extensively studied models in bandit and online learning research. Recently, there has been increasing interest in designing \emph{locally private} linear contextual bandit algor
Externí odkaz:
http://arxiv.org/abs/2404.09413
Autor:
Li, Jiachun, Cao, Pengfei, Wang, Chenhao, Jin, Zhuoran, Chen, Yubo, Zeng, Daojian, Liu, Kang, Zhao, Jun
Large language models exhibit high-level commonsense reasoning abilities, especially with enhancement methods like Chain-of-Thought (CoT). However, we find these CoT-like methods lead to a considerable number of originally correct answers turning wro
Externí odkaz:
http://arxiv.org/abs/2402.18344