no code implementations • 11 Dec 2023 • Haotian Zhang, Semujju Stuart Dereck, Zhicheng Wang, Xianwei Lv, Kang Xu, Liang Wu, Ye Jia, Jing Wu, Zhuo Long, Wensheng Liang, X. G. Ma, Ruiyan Zhuang
Although the applications of artificial intelligence especially deep learning had greatly improved various aspects of intelligent manufacturing, they still face challenges for wide employment due to the poor generalization ability, difficulties to establish high-quality training datasets, and unsatisfactory performance of deep learning methods.
1 code implementation • NeurIPS 2023 • Haoran He, Chenjia Bai, Kang Xu, Zhuoran Yang, Weinan Zhang, Dong Wang, Bin Zhao, Xuelong Li
Specifically, we propose Multi-Task Diffusion Model (\textsc{MTDiff}), a diffusion-based method that incorporates Transformer backbones and prompt learning for generative planning and data synthesis in multi-task offline settings.
no code implementations • 28 May 2023 • Kang Xu, Chenjia Bai, Shuang Qiu, Haoran He, Bin Zhao, Zhen Wang, Wei Li, Xuelong Li
Leveraging learned strategies in unfamiliar scenarios is fundamental to human intelligence.
1 code implementation • journal 2023 • Kang Xu, Weixin Li, Xia Wang, Xiaoyan Hu, Ke Yan, Xiaojie Wang, Xuan Dong
Based on the prior that, for each pixel, its similar pixels are usually spatially close, our insights are that (1) we partition the image into non-overlapped windows and perform regional self-attention to reduce the search range of each pixel, and (2) we encourage pixels across different windows to communicate with each other.
no code implementations • 24 Sep 2022 • Kang Xu, Yan Ma, Bingsheng Wei, Wei Li
While Reinforcement Learning can achieve impressive results for complex tasks, the learned policies are generally prone to fail in downstream tasks with even minor model mismatch or unexpected perturbations.
no code implementations • 23 Sep 2022 • Kang Xu, Yan Ma, Wei Li
Our key insight is that dynamic systems with different parameters provide different levels of difficulty for the policy, and the difficulty of behaving well in a system is constantly changing due to the evolution of the policy.
no code implementations • 12 Mar 2022 • Kang Xu, Xiaoqiu Lu, Yuan-Fang Li, Tongtong Wu, Guilin Qi, Ning Ye, Dong Wang, Zheng Zhou
NTM-DMIE is a neural network method for topic learning which maximizes the mutual information between the input documents and their latent topic representation.
no code implementations • 12 Jan 2022 • Yan Ma, Tianxing Liu, Bingsheng Wei, Yi Liu, Kang Xu, Wei Li
Evolutionary Algorithms (EAs) and Deep Reinforcement Learning (DRL) have recently been integrated to take the advantage of the both methods for better exploration and exploitation. The evolutionary part in these hybrid methods maintains a population of policy networks. However, existing methods focus on optimizing the parameters of policy network, which is usually high-dimensional and tricky for EA. In this paper, we shift the target of evolution from high-dimensional parameter space to low-dimensional action space. We propose Evolutionary Action Selection-Twin Delayed Deep Deterministic Policy Gradient (EAS-TD3), a novel hybrid method of EA and DRL. In EAS, we focus on optimizing the action chosen by the policy network and attempt to obtain high-quality actions to promote policy learning through an evolutionary algorithm.
no code implementations • 9 May 2020 • Junheng Huang, Lu Pan, Kang Xu, Weihua Peng, Fayuan Li
In this paper, we propose a novel generation model based on Topic-aware Pointer-Generator Networks (TPGN), which can utilize the topic information hidden in the articles to guide the generation of pertinent and diversified comments.
no code implementations • 29 Oct 2018 • Kang Xu, Song Bin, Guo Jie, Du Xiaojiang, Guizani Mohsen
Aiming at the problem that the traditional convolutional neural network is vulnerable to background interference, this paper proposes vehicle tracking method based on human attention mechanism for self-selection of deep features with an inter-channel fully connected layer.
no code implementations • 1 Aug 2016 • Beishui Liao, Kang Xu, Huaxin Huang
The results show that our approach not only dramatically decreases the time for computing p(E^\sigma), but also has an attractive property, which is contrary to that of existing approaches: the denser the edges of a PrAG are or the bigger the size of a given extension E is, the more efficient our approach computes p(E^\sigma).