检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Gong, Haisong Liu, Qiang Wu, Shu Wang, Liang Center for Research on Intelligent Perception and Computing State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China

Text-guided molecule generation is a task where molecules are generated to match specific textual descriptions. Recently, most existing SMILES-based molecule generation methods rely on an autoregressive architecture. In this work, we propose the Text-Guided Molecule Generation with Diffusion Language Model (TGM-DLM), a novel approach that leverages diffusion models to address the limitations of autoregressive methods. TGM-DLM updates token embeddings within the SMILES string collectively and iteratively, using a two-phase diffusion generation process. The first phase optimizes embeddings from random noise, guided by the text description, while the second phase corrects invalid SMILES strings to form valid molecular representations. We demonstrate that TGM-DLM outperforms MolT5-Base, an autoregressive model, without the need for additional data resources. Our findings underscore the remarkable effectiveness of TGM-DLM in generating coherent and precise molecules with specific properties, opening new avenues in drug discovery and related scientific domains. Code will be released at: https://***/Deno-V/tgm-dlm. Copyright © 2024, The Authors. All rights reserved.

关键词： Molecules

来源：评论

学校读者我要写书评

暂无评论

Optimal simulation of Deutsch gates and the Fredkin gate

引用

Physical Review A 2015年第3期91卷 032302-032302页

作者： Nengkun Yu Mingsheng Ying Institute for Quantum Computing University of Waterloo Waterloo Ontario Canada Department of Mathematics & Statistics University of Guelph Guelph Ontario Canada Center for Quantum Computation and Intelligent Systems (QCIS) Faculty of Engineering and Information Technology University of Technology Sydney NSW 2007 Australia State Key Laboratory of Intelligent Technology and Systems Tsinghua National Laboratory for Information Science and Technology Department of Computer Science and Technology Tsinghua University Beijing 100084 China

In this paper, we study the optimal simulation of the three-qubit unitary using two-qubit gates. First, we completely characterize the two-qubit gate cost of simulating the Deutsch gate (controlled-controlled gate) by generalizing our result on the two-qubit cost of the Toffoli gate. The function of any Deutsch gate is simply a three-qubit controlled-unitary gate and can be intuitively explained as follows: The gate outputs the states of the two control qubits directly, and applies the given one-qubit unitary u on the target qubit only if both the states of the control qubits are |1〉. Previously, it was only known that five two-qubit gates are sufficient for implementing such a gate [Sleator and Weinfurter, Phys. Rev. Lett. 74, 4087 (1995)]. We show that if the determinant of u is 1, four two-qubit gates are optimal. Otherwise, five two-qubit gates are required. For the Fredkin gate (the controlled-swap gate), we prove that five two-qubit gates are necessary and sufficient, which settles the open problem introduced in Smolin and DiVincenzo [Phys. Rev. A 53, 2855 (1996)].

关键词： QUANTUM gates PARTICLE interactions QUBITS QUANTUM information science QUANTUM fluctuations HAMILTONIAN systems QUANTUM states

来源：评论

学校读者我要写书评

暂无评论

Interpretable Multimodal Out-of-Context Detection with Soft Logic Regularization

Interpretable Multimodal Out-of-Context Detection with Soft ...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Huanhuan Ma Jinghao Zhang Qiang Liu Shu Wu Liang Wang School of Artificial Intelligence University of Chinese Academy of Sciences Center for Research on Intelligent Perception and Computing (CRIPAC) State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS) Institute of Automation Chinese Academy of Sciences

The rapid spread of information through mobile devices and media has led to the widespread of false or deceptive news, causing significant concerns in society. Among different types of misinformation, image repurposing, also known as out-of-context misinformation, remains highly prevalent and effective. However, current approaches for detecting out-of-context misinformation often lack interpretability and offer limited explanations. In this study, we propose a logic regularization approach for out-of-context detection called LOGRAN (LOGic Regularization for out-of-context ANalysis). The primary objective of LOGRAN is to decompose the out-of-context detection at the phrase level. By employing latent variables for phrase-level predictions, the final prediction of the image-caption pair can be aggregated using logical rules. The latent variables also provide an explanation for how the final result is derived, making this fine-grained detection method inherently explanatory. We evaluate the performance of LOGRAN on the NewsCLIPpings dataset, showcasing competitive overall results. Visualized examples also reveal faithful phrase-level predictions of out-of-context images, accompanied by explanations. This highlights the effectiveness of our approach in addressing out-of-context detection and enhancing interpretability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Rethinking Graph Masked Autoencoders through Alignment and Uniformity

arXiv

引用

arXiv 2024年

作者： Wang, Liang Tao, Xiang Liu, Qiang Wu, Shu Wang, Liang Center for Research on Intelligent Perception and Computing State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China

Self-supervised learning on graphs can be bifurcated into contrastive and generative methods. Contrastive methods, also known as graph contrastive learning (GCL), have dominated graph self-supervised learning in the past few years, but the recent advent of graph masked autoencoder (GraphMAE) rekindles the momentum behind generative methods. Despite the empirical success of GraphMAE, there is still a dearth of theoretical understanding regarding its efficacy. Moreover, while both generative and contrastive methods have been shown to be effective, their connections and differences have yet to be thoroughly investigated. Therefore, we theoretically build a bridge between GraphMAE and GCL, and prove that the node-level reconstruction objective in GraphMAE implicitly performs context-level GCL. Based on our theoretical analysis, we further identify the limitations of the GraphMAE from the perspectives of alignment and uniformity, which have been considered as two key properties of high-quality representations in GCL. We point out that GraphMAE's alignment performance is restricted by the masking strategy, and the uniformity is not strictly guaranteed. To remedy the aforementioned limitations, we propose an Alignment- Uniformity enhanced Graph Masked AutoEncoder, named AUG-MAE. Specifically, we propose an easy-to-hard adversarial masking strategy to provide hard-to-align samples, which improves the alignment performance. Meanwhile, we introduce an explicit uniformity regularizer to ensure the uniformity of the learned representations. Experimental results on benchmark datasets demonstrate the superiority of our model over existing state-of-the-art methods. The code is available at: https://***/AzureLeon1/AUG-MAE. Copyright © 2024, The Authors. All rights reserved.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

Can Large Language Models Detect Rumors on Social Media?

arXiv

引用

arXiv 2024年

作者： Liu, Qiang Tao, Xiang Wu, Junfei Wu, Shu Wang, Liang Center for Research on Intelligent Perception and Computing State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China

In this work, we investigate to use Large Language Models (LLMs) for rumor detection on social media. However, it is challenging for LLMs to reason over the entire propagation information on social media, which contains news contents and numerous comments, due to LLMs may not concentrate on key clues in the complex propagation information, and have trouble in reasoning when facing massive and redundant information. Accordingly, we propose an LLM-empowered Rumor Detection (LeRuD) approach, in which we design prompts to teach LLMs to reason over important clues in news and comments, and divide the entire propagation information into a Chain-of-Propagation for reducing LLMs’ burden. We conduct extensive experiments on the Twitter and Weibo datasets, and LeRuD outperforms several state-of-the-art rumor detection models by 3.2% to 7.7%. Meanwhile, by applying LLMs, LeRuD requires no data for training, and thus shows more promising rumor detection ability in few-shot or zero-shot scenarios. © 2024, CC BY.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Learning Greenhouse Climate Control Policy from Monitored Data

Learning Greenhouse Climate Control Policy from Monitored Da...

引用

2022 Chinese Automation Congress, CAC 2022

作者： Zhao, Xiaoxuan Wang, Haoyu Wang, Xiujuan Lewlomphaisarl, Udom Li, Dong Hua, Jing Kang, Mengzhen The State Key Laboratory for Management and Control of Complex Systems Chinese Academy of Sciences Institute of Automation Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Beijing Engineering Research Center of Intelligent Systems and Technologies Beijing China National Electronics and Computer Technology Center Pathum Thani Thailand Institute of Digital Agriculture Zhejiang Academy of Agricultural Sciences Hangzhou China Qingdao AgriTech Co. Ltd. Qingdao China

ISBN: (纸本)9781665465335

The knowledge of solar greenhouse growers on environment control plays an important role in greenhouse production and management. We proposed a way to extract the control strategies from the monitored data of greenhouses by building a long short-term memory (LSTM) model. The result is verified according to the real monitored data of a solar greenhouse, which shows that the model can learn the control strategy of a ventilator in the solar greenhouse. Through monitored data and models, the knowledge of greenhouse ventilation control can be learned, and automatic control can be achieved in a greenhouse with a similar configuration. © 2022 IEEE.

关键词： Greenhouses

来源：评论

学校读者我要写书评

暂无评论

Boosting generative models by leveraging cascaded meta-models

arXiv

引用

arXiv 2019年

作者： Bao, Fan Su, Hang Zhu, Jun Institute for Artificial Intelligence State Key Laboratory of Intelligent Technology and Systems Beijing National Research Center for Information Science and Technology Department of Computer Science and Technology Tsinghua University Beijing100084

Deep generative models are effective methods of modeling data. However, it is not easy for a single generative model to faithfully capture the distributions of complex data such as images. In this paper, we propose an approach for boosting generative models, which cascades meta-models together to produce a stronger model. Any hidden variable meta-model (e.g., RBM and VAE) which supports likelihood evaluation can be leveraged. We derive a decomposable variational lower bound of the boosted model, which allows each meta-model to be trained separately and greedily. Besides, our framework can be extended to semi-supervised boosting, where the boosted model learns a joint distribution of data and labels. Finally, we combine our boosting framework with the multiplicative boosting framework, which further improves the learning power of generative models. Copyright © 2019, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Real-time In-situ Defect Detection in 3D Printing of Continuous Fiber-Reinforced Composites

Real-time In-situ Defect Detection in 3D Printing of Continu...

引用

Digital Twins and Parallel Intelligence (DTPI), IEEE International Conference on

作者： Zhijian Yue Zhen Shen Xiangyang Dong Qihang Fang Weixing Wang Xisong Dong Gang Xiong Fei-Yue Wang School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China State Key Laboratory of Multimodal Artificial Intelligence Systems Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences Beijing China Intelligent Manufacturing Center Qingdao Academy of Intelligent Industries Qingdao China Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences Dongguan China State Key Laboratory for Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (数字)9798350349252

ISBN: (纸本)9798350349269

With the development of continuous fiber-reinforced composites (CFRCs) 3D printing technology, timely, efficient and accurate detection of fiber path defects is essential for ensuring product quality and performance. However, challenges still need to be addressed in this field, such as inadequate training data coverage and the complexity of fiber path structures. These factors hinder the capability of traditional methods to accurately assess the status of printed products. Therefore, developing accurate and robust fiber path defect detection techniques is crucial for CFRCs 3D printing technology. In this paper, we propose a precise detection method for fiber path defects in CFRCs 3D printing using the YOLOv7 object detection model combined with a Squeeze-and-Excitation (SE) attention mechanism. By introducing the SE attention mechanism, we enhance the perception capability of the YOLOv7 model for crucial features, thereby improving the accuracy of fiber path defect detection. The experimental results show that the YOLOv7 model, when augmented with an attention mechanism, achieves an average accuracy of 93.9% in identifying fiber path defects during the printing process. Compared to models without this attention mechanism, the results show that there is 10.7% increase, with a notably enhanced learning capacity during the training phase, which substantiates the efficacy and practicality of the proposed approach.

关键词： Training Solid modeling Accuracy Attention mechanisms Training data Three-dimensional printing Real-time systems Quality assessment Optical fiber testing Defect detection

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning for Dynamic Error Compensation in 3D Printing

Deep Reinforcement Learning for Dynamic Error Compensation i...

引用

IEEE International Conference on Automation Science and Engineering (CASE)

作者： Dong Wang Zhen Shen Xiangyang Dong Qihang Fang Weixing Wang Xisong Dong Gang Xiong School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China Intelligent Manufacturing Center Qingdao Academy of Intelligent Industries Qingdao China State Key Laboratory of Multimodal Artificial Intelligence Systems Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences Beijing China Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences Dongguan China

In the 3D printing process, various error factors can affect the accuracy of the final printing quality. However, current 3D printing error compensation methods have limited effects and usually cannot work in real-time. The 3D printing error compensation process is modeled as a Markov decision process (MDP) in this paper, and Deep Reinforcement Learning (DRL) is applied for dynamic error compensation. This method learns autonomously through trial and error by interacting with the printing environment, which makes it adaptable to various types of 3D printers without specific training. Then, we simulate the digital light processing (DLP) 3D printing. Due to the huge state and action space of sliced images, applying the DRL algorithm to DLP is challenging. We propose an error compensation method based on morphological image operation and use Autoencoder to extract error features to reduce the state space. We then implement our method using a Twin Delayed Deep Deterministic policy gradient algorithm (TD3). The results demonstrate the effects of our method in compensating 3D printing errors.

关键词：

来源：评论

学校读者我要写书评

暂无评论

GSLB: The Graph Structure Learning Benchmark 37

GSLB: The Graph Structure Learning Benchmark

引用

37th Conference on Neural Information Processing systems, NeurIPS 2023

作者： Li, Zhixun Wang, Liang Sun, Xin Luo, Yifan Zhu, Yanqiao Chen, Dingshuo Luo, Yingtao Zhou, Xiangxin Liu, Qiang Wu, Shu Yu, Jeffrey Xu Department of Systems Engineering and Engineering Management The Chinese University of Hong Kong Hong Kong Center for Research on Intelligent Perception and Computing State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China Department of Automation University of Science and Technology of China China School of Cyberspace Security Beijing University of Posts and Telecommunications China Department of Computer Science University of California Los Angeles United States Heinz College of Information Systems and Public Policy Machine Learning Department School of Computer Science Carnegie Mellon University United States

ISBN: (纸本)9781713899921

Graph Structure Learning (GSL) has recently garnered considerable attention due to its ability to optimize both the parameters of Graph Neural Networks (GNNs) and the computation graph structure simultaneously. Despite the proliferation of GSL methods developed in recent years, there is no standard experimental setting or fair comparison for performance evaluation, which creates a great obstacle to understanding the progress in this field. To fill this gap, we systematically analyze the performance of GSL in different scenarios and develop a comprehensive Graph Structure Learning Benchmark (GSLB) curated from 20 diverse graph datasets and 16 distinct GSL algorithms. Specifically, GSLB systematically investigates the characteristics of GSL in terms of three dimensions: effectiveness, robustness, and complexity. We comprehensively evaluate state-of-the-art GSL algorithms in node- and graph-level tasks, and analyze their performance in robust learning and model complexity. Further, to facilitate reproducible research, we have developed an easy-to-use library for training, evaluating, and visualizing different GSL methods. Empirical results of our extensive experiments demonstrate the ability of GSL and reveal its potential benefits on various downstream tasks, offering insights and opportunities for future research. The code of GSLB is available at: https://***/GSL-Benchmark/GSLB. © 2023 Neural information processing systems foundation. All rights reserved.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：