Zobrazeno 1 - 10
of 560
pro vyhledávání: '"HAN Jiaqi"'
Publikováno v:
智能科学与技术学报, Vol 6, Pp 381-393 (2024)
In response to the potential risk of backdoor attacks faced by artificial intelligence systems, a range of backdoor defense strategies are developed. The diversity of the evaluation criteria for existing defense method, makes cross-method comparisons
Externí odkaz:
https://doaj.org/article/7406a82e802a4f3685b98d05f0ab4747
Publikováno v:
Journal of Aeronautical Materials, Vol 44, Iss 3, Pp 65-81 (2024)
The application of compressor blisk is one of the typical technologies of high-performance engines. However，due to its contact with high-speed airflow containing various solids，a variety of different forms of structural damage and performance deg
Externí odkaz:
https://doaj.org/article/37da613a23224eedb3076bf90132ddb4
Publikováno v:
Nanophotonics, Vol 11, Iss 9, Pp 1697-1723 (2022)
In the last two decades, metamaterials and metasurfaces have introduced many new electromagnetic (EM) theory concepts and inspired contemporary design methodologies for EM devices and systems. This review focuses on the recent advances in metamateria
Externí odkaz:
https://doaj.org/article/2b6d7918f1c94f1aaa851edc2f6ce19f
Preference optimization has made significant progress recently, with numerous methods developed to align language models with human preferences. This paper introduces $f$-divergence Preference Optimization ($f$-PO), a novel framework that generalizes
Externí odkaz:
http://arxiv.org/abs/2410.21662
Generative models have shown great promise in generating 3D geometric systems, which is a fundamental problem in many natural science domains such as molecule and protein design. However, existing approaches only operate on static structures, neglect
Externí odkaz:
http://arxiv.org/abs/2410.13027
Autor:
Ye, Haotian, Lin, Haowei, Han, Jiaqi, Xu, Minkai, Liu, Sheng, Liang, Yitao, Ma, Jianzhu, Zou, James, Ermon, Stefano
Given an unconditional diffusion model and a predictor for a target property of interest (e.g., a classifier), the goal of training-free guidance is to generate samples with desirable target properties without additional training. Existing methods, t
Externí odkaz:
http://arxiv.org/abs/2409.15761
Diffusion models have a tendency to exactly replicate their training data, especially when trained on small datasets. Most prior work has sought to mitigate this problem by imposing differential privacy constraints or masking parts of the training da
Externí odkaz:
http://arxiv.org/abs/2409.07025
Autor:
Robinson, Joshua, Ranjan, Rishabh, Hu, Weihua, Huang, Kexin, Han, Jiaqi, Dobles, Alejandro, Fey, Matthias, Lenssen, Jan E., Yuan, Yiwen, Zhang, Zecheng, He, Xinwei, Leskovec, Jure
We present RelBench, a public benchmark for solving predictive tasks over relational databases with graph neural networks. RelBench provides databases and tasks spanning diverse domains and scales, and is intended to be a foundational infrastructure
Externí odkaz:
http://arxiv.org/abs/2407.20060
Autor:
You, Yang, Uy, Mikaela Angelina, Han, Jiaqi, Thomas, Rahul, Zhang, Haotong, You, Suya, Guibas, Leonidas
Reverse engineering 3D computer-aided design (CAD) models from images is an important task for many downstream applications including interactive editing, manufacturing, architecture, robotics, etc. The difficulty of the task lies in vast representat
Externí odkaz:
http://arxiv.org/abs/2408.01437
We present exact solutions describing dynamics of two algebraic solitons in the massive Thirring model. Each algebraic soliton corresponds to a simple embedded eigenvalue in the Kaup--Newell spectral problem and attains the maximal mass among the fam
Externí odkaz:
http://arxiv.org/abs/2406.06715