Zobrazeno 1 - 10
of 316
pro vyhledávání: '"An, Dingling"'
We propose Scalable Mechanistic Neural Network (S-MNN), an enhanced neural network framework designed for scientific machine learning applications involving long temporal sequences. By reformulating the original Mechanistic Neural Network (MNN) (Perv
Externí odkaz:
http://arxiv.org/abs/2410.06074
Causal representation learning aims at recovering latent causal variables from high-dimensional observations to solve causal downstream tasks, such as predicting the effect of new interventions or more robust classification. A plethora of methods hav
Externí odkaz:
http://arxiv.org/abs/2409.02772
Autor:
Zhu, Kunlun, Luo, Yifan, Xu, Dingling, Wang, Ruobing, Yu, Shi, Wang, Shuo, Yan, Yukun, Liu, Zhenghao, Han, Xu, Liu, Zhiyuan, Sun, Maosong
Retrieval-Augmented Generation (RAG) is a powerful approach that enables large language models (LLMs) to incorporate external knowledge. However, evaluating the effectiveness of RAG systems in specialized scenarios remains challenging due to the high
Externí odkaz:
http://arxiv.org/abs/2408.01262
Causal representation learning promises to extend causal models to hidden causal variables from raw entangled measurements. However, most progress has focused on proving identifiability results in different settings, and we are not aware of any succe
Externí odkaz:
http://arxiv.org/abs/2405.13888
Autor:
Xu, Danru, Yao, Dingling, Lachapelle, Sébastien, Taslakian, Perouz, von Kügelgen, Julius, Locatello, Francesco, Magliacane, Sara
Causal representation learning aims at identifying high-level causal variables from perceptual data. Most methods assume that all latent causal variables are captured in the high-dimensional observations. We instead consider a partially observed sett
Externí odkaz:
http://arxiv.org/abs/2403.08335
Autor:
Yao, Dingling, Xu, Danru, Lachapelle, Sébastien, Magliacane, Sara, Taslakian, Perouz, Martius, Georg, von Kügelgen, Julius, Locatello, Francesco
We present a unified framework for studying the identifiability of representations learned from simultaneously observed views, such as different data modalities. We allow a partially observed setting in which each view constitutes a nonlinear mixture
Externí odkaz:
http://arxiv.org/abs/2311.04056
Autor:
Cheng Qiu, Lin Cheng, Jingwei Liu, Zhiguo Ding, Musen Sun, Yanyong Yu, Dingling An, Lianlei Wang, Xianlei Gao, Xin Pan, Xinyu Liu, Songgang Wang
Publikováno v:
Orthopaedic Surgery, Vol 16, Iss 7, Pp 1592-1602 (2024)
Objective Thoracolumbar fractures are one of the most common fractures in clinical practice. Surgical intervention is recommended to restore spinal alignment or decompress the nerves when there are unstable fractures or neurological injuries. However
Externí odkaz:
https://doaj.org/article/c44da5d7142d4c4495d222de61d44693
Autor:
Chen Zhang, Taili Dong, Fang Li, Geng Chen, Zilong Guo, Dingling Yuan, Songyi Chen, Kanghua Chen
Publikováno v:
Journal of Materials Research and Technology, Vol 30, Iss , Pp 6163-6175 (2024)
Inhomogeneous microstructures and alloy chemistry along the thickness direction can greatly affect the mechanical and corrosion properties of new generation 7xxx aluminum alloy thick plates. The inhomogeneous microstructure, stress corrosion cracking
Externí odkaz:
https://doaj.org/article/c64033184b09474daad4df1203f578a8
Publikováno v:
In Brain Research 15 December 2024 1845
Autor:
Xue, Runbo, Li, Min, Pan, Jin, Yuan, Dingling, Yang, Yan, Hao, Xiaofeng, Pang, Xiangchao, Zeng, Fan, Zhu, Yuan
Publikováno v:
In Progress in Organic Coatings December 2024 197