no code implementations • 3 May 2023 • Qihan Ren, Jiayang Gao, Wen Shen, Quanshi Zhang
This paper aims to prove the emergence of symbolic concepts in well-trained AI models.
no code implementations • 3 Apr 2023 • Wen Shen, Lei Cheng, Yuxiao Yang, Mingjie Li, Quanshi Zhang
In this paper, we explain the inference logic of large language models (LLMs) as a set of symbolic concepts.
no code implementations • 25 Feb 2023 • Huilin Zhou, Hao Zhang, Huiqi Deng, Dongrui Liu, Wen Shen, Shih-Han Chan, Quanshi Zhang
Therefore, in this paper, we investigate the generalization power of each interactive concept, and we use the generalization power of different interactive concepts to explain the generalization power of the entire DNN.
no code implementations • 17 Oct 2022 • Ling Tang, Wen Shen, Zhanpeng Zhou, Yuefeng Chen, Quanshi Zhang
In this paper, we prove the representation defects of a cascaded convolutional decoder network, considering the capacity of representing different frequency components of an input sample.
no code implementations • 30 May 2022 • Zhanpeng Zhou, Wen Shen, Huixin Chen, Ling Tang, Quanshi Zhang
In this paper, we prove the effects of the BN operation on the back-propagation of the first and second derivatives of the loss.
no code implementations • 30 May 2022 • Xu Cheng, Hao Zhang, Yue Xin, Wen Shen, Jie Ren, Quanshi Zhang
We also prove that adversarial training tends to strengthen the influence of unconfident input samples with large gradient norms in an exponential manner.
no code implementations • NeurIPS 2021 • Wen Shen, Qihan Ren, Dongrui Liu, Quanshi Zhang
In this paper, we evaluate the quality of knowledge representations encoded in deep neural networks (DNNs) for 3D point cloud processing.
no code implementations • 29 Sep 2021 • Wen Shen, Henger Li, Zizhan Zheng
We propose a model-based multi-agent reinforcement learning attack framework against federated learning systems.
1 code implementation • 9 Jul 2021 • Wen Shen, Zhihua Wei, Shikun Huang, BinBin Zhang, Jiaqi Fan, Ping Zhao, Quanshi Zhang
The reasonable definition of semantic interpretability presents the core challenge in explainable AI.
no code implementations • 3 Aug 2020 • Chao Chai, Pengchong Qiao, Bin Zhao, Huiying Wang, Guohua Liu, Hong Wu, E Mark Haacke, Wen Shen, Chen Cao, Xinchen Ye, Zhiyang Liu, Shuang Xia
Abnormal iron accumulation in the brain subcortical nuclei has been reported to be correlated to various neurodegenerative diseases, which can be measured through the magnetic susceptibility from the quantitative susceptibility mapping (QSM).
1 code implementation • ECCV 2020 • Wen Shen, BinBin Zhang, Shikun Huang, Zhihua Wei, Quanshi Zhang
This paper proposes a set of rules to revise various neural networks for 3D point cloud processing to rotation-equivariant quaternion neural networks (REQNNs).
1 code implementation • CVPR 2021 • Wen Shen, Zhihua Wei, Shikun Huang, BinBin Zhang, Panyue Chen, Ping Zhao, Quanshi Zhang
In this paper, we diagnose deep neural networks for 3D point cloud processing to explore utilities of different intermediate-layer network architectures.
no code implementations • 12 Sep 2017 • Wen Shen, Jacob W. Crandall, Ke Yan, Cristina V. Lopes
We introduce a heuristic algorithm to dynamically compute information-disclosure policies for the entrepreneur, followed by an empirical evaluation to demonstrate its competitiveness over the widely-adopted immediate-disclosure policy.
no code implementations • 7 Aug 2017 • Wen Shen, Alanoud Al Khemeiri, Abdulla Almehrezi, Wael Al Enezi, Iyad Rahwan, Jacob W. Crandall
As in the study of political systems in which governments regulate human societies, our studies analyze how interactions between HARE and regulators are impacted by regulatory power and individual (robot or agent) autonomy.
no code implementations • 7 Mar 2016 • Wen Shen, Cristina V. Lopes, Jacob W. Crandall
With proper management, Autonomous Mobility-on-Demand (AMoD) systems have great potential to satisfy the transport demands of urban populations by providing safe, convenient, and affordable ridesharing services.
no code implementations • 9 Jul 2015 • Wen Shen, Cristina Lopes
Autonomous mobility on demand systems, though still in their infancy, have very promising prospects in providing urban population with sustainable and safe personal mobility in the near future.