Zobrazeno 1 - 10
of 536
pro vyhledávání: '"Wei, Zihao"'
Recent knowledge editing methods have primarily focused on modifying structured knowledge in large language models. However, this task setting overlooks the fact that a significant portion of real-world knowledge is stored in an unstructured format,
Externí odkaz:
http://arxiv.org/abs/2405.15349
We propose a simple strategy for masking image patches during visual-language contrastive learning that improves the quality of the learned representations and the training speed. During each iteration of training, we randomly mask clusters of visual
Externí odkaz:
http://arxiv.org/abs/2405.08815
The extensive utilization of large language models (LLMs) underscores the crucial necessity for precise and contemporary knowledge embedded within their intrinsic parameters. Existing research on knowledge editing primarily concentrates on monolingua
Externí odkaz:
http://arxiv.org/abs/2404.04990
Volumetric optical microscopy using non-diffracting beams enables rapid imaging of 3D volumes by projecting them axially to 2D images but lacks crucial depth information. Addressing this, we introduce MicroDiffusion, a pioneering tool facilitating hi
Externí odkaz:
http://arxiv.org/abs/2403.10815
Efficient knowledge editing of large language models is crucial for replacing obsolete information or incorporating specialized knowledge on a large scale. However, previous methods implicitly assume that knowledge is localized and isolated within th
Externí odkaz:
http://arxiv.org/abs/2402.13048
Hallucinations pose a significant challenge for the practical implementation of large language models (LLMs). The utilization of parametric knowledge in generating factual content is constrained by the limited knowledge of LLMs, potentially resulting
Externí odkaz:
http://arxiv.org/abs/2402.10612
Autor:
Wang, Yiqing, Li, Zihan, Mei, Jieru, Wei, Zihao, Liu, Li, Wang, Chen, Sang, Shengtian, Yuille, Alan, Xie, Cihang, Zhou, Yuyin
Recent advancements in large-scale Vision Transformers have made significant strides in improving pre-trained models for medical image segmentation. However, these methods face a notable challenge in acquiring a substantial amount of pre-training dat
Externí odkaz:
http://arxiv.org/abs/2307.12591
Multi-aspect controllable text generation aims to generate fluent sentences that possess multiple desired attributes simultaneously. Traditional methods either combine many operators in the decoding stage, often with costly iteration or search in the
Externí odkaz:
http://arxiv.org/abs/2305.12785
Gradient Boosting Machines (GBMs) have demonstrated remarkable success in solving diverse problems by utilizing Taylor expansions in functional space. However, achieving a balance between performance and generality has posed a challenge for GBMs. In
Externí odkaz:
http://arxiv.org/abs/2209.13791
The aim of this paper is to demonstrate the efficacy of using Contrastive Random Walk as a curiosity method to achieve faster convergence to the optimal policy.Contrastive Random Walk defines the transition matrix of a random walk with the help of ne
Externí odkaz:
http://arxiv.org/abs/2204.10976