检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on Artificial intelligence, AAAI 2025

作者： Huang, Changxin Chang, Yanbin Lin, Junfan Liang, Junyang Zeng, Runhao Li, Jianqiang National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Peng Cheng Laboratory Shenzhen China Artificial Intelligence Research Institute Shenzhen MSU-BIT University Shenzhen China

ISBN: (纸本)157735897X

The ability to autonomously explore and resolve tasks with minimal human guidance is crucial for the self-development of embodied intelligence. Although reinforcement learning methods can largely ease human effort, it’s challenging to design reward functions for real-world tasks, especially for high-dimensional robotic control, due to complex relationships among joints and tasks. Recent advancements large language models (LLMs) enable automatic reward function design. However, approaches evaluate reward functions by retraining policies from scratch placing an undue burden on the reward function, expecting it to be effective throughout the whole policy improvement process. We argue for a more practical strategy in robotic autonomy, focusing on refining existing policies with policy-dependent reward functions rather than a universal one. To this end, we propose a novel reward-policy co-evolution framework where the reward function and the learned policy benefit from each other’s progressive on-the-fly improvements, resulting in more efficient and higher-performing skill acquisition. Specifically, the reward evolution process translates the robot’s previous best reward function, descriptions of tasks and environment into text inputs. These inputs are used to query LLMs to generate a dynamic amount of reward function candidates, ensuring continuous improvement at each round of evolution. For policy evolution, our method generates new policy populations by hybridizing historically optimal and random policies. Through an improved Bayesian optimization, our approach efficiently and robustly identifies the most capable and plastic reward-policy combination, which then proceeds to the next round of co-evolution. Despite using less data, our approach demonstrates an average normalized improvement of 95.3% across various high-dimensional robotic skill learning tasks. Copyright © 2025, Association for the Advancement of Artificial intelligence (***). All rights reserve

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Marine Predator Algorithm for Thermal-aware Routing Scheme in Wireless Body Area Networks

引用

Journal of Bionic Engineering 2023年第1期20卷 81-104页

作者： Tao Hai Jincheng Zhou Mohammad Masdari Haydar Abdulameer Marhoon School of Computer and Information Qiannan Normal University for NationalitiesDuyun558000GuizhouChina Key Laboratory of Complex Systems and Intelligent Optimization of Guizhou Duyun558000GuizhouChina Institute for Big Data Analytics and Artificial Intelligence(IBDAAI) Universiti Teknologi MARA40450Shah AlamSelangorMalaysia Department of Computer Engineering Islamic Azad UniversityUrmia BranchUrmiaIran Information and Communication Technology Research Group Scientific Research CenterAl-Ayen UniversityThi-QarIraq College of Computer Sciences and Information Technology University of KerbalaKarbalaIraq

Thermal-aware routing protocols in WBANs consider temperature factors in the routing process for preventing overheating of the tissues surrounding the sensor ***,providing an energy-efficient and thermal-aware routing in WBANs is a challenging *** deal with this problem,this article presents a novel temperature-aware routing protocol that applies Mamdani-based Fuzzy Logic Controllers(FLCs)for selecting the next forwarding node in routing data *** FLCs apply five important input factors such as the priority of the packet,and sensor node's remaining energy,temperature,distance,and link path ***,a new hybrid version of the Marine Predator Algorithm(MPA),named MPAOA is presented by combining the exploration and exploitation phases of the MPA and Arithmetic Optimization Algorithm(AOA).This algorithm is effectively applied for selecting the best possible set of fuzzy rules for FLCs and tuning their fuzzy *** experiments conducted in the Castalia simulator exhibit that the proposed temperature and priority-aware routing scheme can outperform other well-known routing schemes such as LATOR,TTRP,TAEO,ATAR,and EOCC-TARA in terms of metrics such as sensor nodes lifetime,the average temperature of the sensor nodes,and the percentage of the packets routed through non-overheated ***,it is shown that the MPAOA outperforms other algorithms such as Bat Algorithm(BA),Genetic Algorithm(GA),AOA,and MPA regarding the specified metrics.

关键词： WBANs Multi-hop routing Temperature Priority Fuzzy logic Bio-inspiration

来源：评论

学校读者我要写书评

暂无评论

ASADA: Attention-Induced Style Alignment Domain Adaptation for Traffic Object Detection

ASADA: Attention-Induced Style Alignment Domain Adaptation f...

引用

Smart World Congress (SWC), IEEE

作者： Xiao Mao Zining Liu Hui Zhang Yidong Li Key Laboratory of Big Data & Artificial Intelligence in Transportation Ministry of Education School of Computer and Information Technology Beijing Jiaotong University Beijing China

The development of deep learning models for intelligent vehicles rely on a large number of reliable data, among which large-scale and accurately labeled traffic scene image data is conducive to promoting the research of intelligent perception algorithms. In contrast to the time-consuming and laborious process of manual annotation, the virtual dataset synthesis method is a convenient and efficient way to replace manual labeling. However, due to the existence of automatically labeled samples in the virtual dataset that are not conducive to model training, and the domain shift between the virtual dataset and the real scene, the model trained from the virtual dataset cannot be well generalized to the real scene. To address these issues, we propose a two-stage label screening strategy for the data processing to remove the interference samples with low information content and further propose a novel efficient traffic scene dataset named Large-Scale Software-Defined Transportation Virtual dataset (LSTVD). Moreover, an attention-induced style alignment domain adaptation method (ASADA) is proposed to reduce the distribution difference between the virtual data domain and the real-world data domain. Experiment results demonstrate the efficiency of our label screening strategy and our domain adaptation method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Step-by-Step: Controlling Arbitrary Style in Text with Large Language Models 30

Step-by-Step: Controlling Arbitrary Style in Text with Large...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Liu, Pusheng Wu, Lianwei Wang, Linyong Guo, Sensen Liu, Yang National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science Northwestern Polytechnical University China Research & Development Institute of Northwestern Polytechnical University Shenzhen China Chongqing Science & Technology Innovation Center of Northwestern Polytechnical University China State Key Laboratory of Integrated Service Networks Xidian University China School of Artificial Intelligence Optics and Electronics Northwestern Polytechnical University China

ISBN: (纸本)9782493814104

Recently, the autoregressive framework based on large language models (LLMs) has achieved excellent performance in controlling the generated text to adhere to the required style. These methods guide LLMs through prompt learning to generate target text in an autoregressive manner. However, this manner possesses lower controllability and suffers from the challenge of accumulating errors, where early prediction inaccuracies might influence subsequent word generation. Furthermore, existing prompt-based methods overlook specific region editing, resulting in a deficiency of localized control over input text. To overcome these challenges, we propose a novel three-stage prompt-based approach for specific region editing. To alleviate the issue of accumulating errors, we transform the text style transfer task into a text infilling task, guiding the LLMs to modify only a small portion of text within the editing region to achieve style transfer, thus reducing the number of autoregressive iterations. To achieve an effective specific editing region, we adopt both prompt-based and word frequency-based strategies for region selection, subsequently employing a discriminator to validate the efficacy of the selected region. Experiments conducted on several publicly competitive datasets for text style transfer task confirm that our proposed approach achieves state-of-the-art performance. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

COCL: Cluster Combined with Outlier Contrast Learning for Unsupervised Person Re-Identification

COCL: Cluster Combined with Outlier Contrast Learning for Un...

引用

Smart World Congress (SWC), IEEE

作者： Zhiqiang Li Yidong Li Key Laboratory of Big Data & Artificial Intelligence in Transportation Ministry of Education School of Computer and Information Technology Beijing Jiaotong University Beijing China

Unsupervised person re-identification (re-ID) is a challenging task which has received extensive attention from the industry. State-of-the-arts unsupervised re-ID methods adopt clustering techniques to generate pseudo labels and train re-ID models progressively with InfoNCE loss. However, they discard the clustering outlier samples during training, which also carry valuable information. In this paper, we propose a new approach making reasonable use of outlier samples, and optimize feature representation at the cluster level. Moreover, we find that using a single memory dictionary update strategy throughout the entire training process is unreasonable. To address this issue, we propose a two-stage training framework. At each stage, we choose the optimal memory dictionary update strategy, which greatly facilitates training. Our method mainly focuses on downstream tasks of unsupervised re-ID and extensive experiments on two popular large-scale re-ID benchmarks demonstrate that our proposed Cluster Combined with Outlier Contrast Learning(COCL) outperforms most unsupervised methods by a significant margin.

关键词：

来源：评论

学校读者我要写书评

暂无评论

RegMixMatch: Optimizing Mixup Utilization in Semi-Supervised Learning

arXiv

引用

arXiv 2024年

作者： Han, Haorong Yuan, Jidong Wei, Chixuan Yu, Zhongyang Key Laboratory of Big Data and Artificial Intelligence in Transportation Ministry of Education China School of Computer Science and Technology Beijing Jiaotong University China School of Data Science and Intelligent Media Communication University of China China

Consistency regularization and pseudo-labeling have significantly advanced semi-supervised learning (SSL). Prior works have effectively employed Mixup for consistency regularization in SSL. However, our findings indicate that applying Mixup for consistency regularization may degrade SSL performance by compromising the purity of artificial labels. Moreover, most pseudo-labeling based methods utilize thresholding strategy to exclude low-confidence data, aiming to mitigate confirmation bias;however, this approach limits the utility of unlabeled samples. To address these challenges, we propose RegMixMatch, a novel framework that optimizes the use of Mixup with both high- and low-confidence samples in SSL. First, we introduce semi-supervised RegMixup, which effectively addresses reduced artificial labels purity by using both mixed samples and clean samples for training. Second, we develop a class-aware Mixup technique that integrates information from the top-2 predicted classes into low-confidence samples and their artificial labels, reducing the confirmation bias associated with these samples and enhancing their effective utilization. Experimental results demonstrate that RegMixMatch achieves state-of-the-art performance across various SSL benchmarks. Copyright © 2024, The Authors. All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Generative Pre-trained Speech Language Model with Efficient Hierarchical Transformer

arXiv

引用

arXiv 2024年

作者： Zhu, Yongxin Su, Dan He, Liqiang Xu, Linli Yu, Dong School of Data Science University of Science and Technology of China China School of Computer Science and Technology University of Science and Technology of China China State Key Laboratory of Cognitive Intelligence China Tencent AI Lab China

While recent advancements in speech language models have achieved significant progress, they face remarkable challenges in modeling the long acoustic sequences of neural audio codecs. In this paper, we introduce Generative Pre-trained Speech Transformer (GPST), a hierarchical transformer designed for efficient speech language modeling. GPST quantizes audio waveforms into two distinct types of discrete speech representations and integrates them within a hierarchical transformer architecture, allowing for a unified one-stage generation process and enhancing Hi-Res audio generation capabilities. By training on large corpora of speeches in an end-to-end unsupervised manner, GPST can generate syntactically consistent speech with diverse speaker identities. Given a brief 3-second prompt, GPST can produce natural and coherent personalized speech, demonstrating in-context learning abilities. Moreover, our approach can be easily extended to spoken cross-lingual speech generation by incorporating multi-lingual semantic tokens and universal acoustic tokens. Experimental results indicate that GPST significantly outperforms the existing speech language models in terms of word error rate, speech quality, and speaker similarity. The code is available at https://***/youngsheen/GPST. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Reform of Blended-Teaching Mode for Discipline English Based on Mobile Terminal 17th

Reform of Blended-Teaching Mode for Discipline English Based...

引用

17th International Conference on Computer Science and Education, ICCSE 2022

作者： Yu, Niefang Peng, Xiaoning Li, Xiaomei Lu, Youmin School of Computer and Artificial Intelligence Huaihua University Hunan Huaihua418000 China Key Laboratory of Wuling-Mountain Health Big Data Intelligent Processing and Application in Hunan Province Universities Hunan Huaihua418000 China Key Laboratory of Intelligent Control Technology for Wuling-Mountain Ecological Agriculture in Hunan Province Hunan Huaihua418000 China

ISBN: (纸本)9789819924455

In the context of the era of big data, the rise of using mobile terminal is also putting forward new requirements for the teaching of Discipline English. Based on some general problems in the teaching practice of this course, we discuss whether adopting the blended-teaching mode can expand the learning space and time, enrich the learning interaction, and improve the learning efficiency in the context of big data based on mobile terminals. And then improve the quality of teaching and enhance application ability for the Discipline English. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： big data

来源：评论

学校读者我要写书评

暂无评论

DFA-GNN: forward learning of graph neural networks by direct feedback alignment 24

DFA-GNN: forward learning of graph neural networks by direct...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Gongpei Zhao Tao Wang Congyan Lang Yi Jin Yidong Li Haibin Ling Key Laboratory of Big Data & Artificial Intelligence in Transportation Ministry of Education China and School of Computer Science & Technology Beijing Jiaotong University China Department of Computer Science Stony Brook University

ISBN: (纸本)9798331314385

Graph neural networks (GNNs) are recognized for their strong performance across various applications, with the backpropagation (BP) algorithm playing a central role in the development of most GNN models. However, despite its effectiveness, BP has limitations that challenge its biological plausibility and affect the efficiency, scalability and parallelism of training neural networks for graph-based tasks. While several non-backpropagation (non-BP) training algorithms, such as the direct feedback alignment (DFA), have been successfully applied to fully-connected and convolutional network components for handling Euclidean data, directly adapting these non-BP frameworks to manage non-Euclidean graph data in GNN models presents significant challenges. These challenges primarily arise from the violation of the independent and identically distributed (i.i.d.) assumption in graph data and the difficulty in accessing prediction errors for all samples (nodes) within the graph. To overcome these obstacles, in this paper we propose DFA-GNN, a novel forward learning framework tailored for GNNs with a case study of semi-supervised learning. The proposed method breaks the limitations of BP by using a dedicated forward training mechanism. Specifically, DFA-GNN extends the principles of DFA to adapt to graph data and unique architecture of GNNs, which incorporates the information of graph topology into the feedback links to accommodate the non-Euclidean characteristics of graph data. Additionally, for semi-supervised graph learning tasks, we developed a pseudo error generator that spreads residual errors from training data to create a pseudo error for each unlabeled node. These pseudo errors are then utilized to train GNNs using DFA. Extensive experiments on 10 public benchmarks reveal that our learning framework outperforms not only previous non-BP methods but also the standard BP methods, and it exhibits excellent robustness against various types of noise and attacks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Generated and pseudo content guided prototype refinement for few-shot point cloud segmentation 24

Generated and pseudo content guided prototype refinement for...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Lili Wei Congyan Lang Ziyi Chen Tao Wang Yidong Li Jun Liu School of Computer Science & Technology Beijing Jiaotong University China and Key Laboratory of Big Data & Artificial Intelligence in Transportation Ministry of Education China School of Computing and Communications Lancaster University UK

ISBN: (纸本)9798331314385

Few-shot 3D point cloud semantic segmentation aims to segment query point clouds with only a few annotated support point clouds. Existing prototype-based methods learn prototypes from the 3D support set to guide the segmentation of query point clouds. However, they encounter the challenge of low prototype quality due to constrained semantic information in the 3D support set and class information bias between support and query sets. To address these issues, in this paper, we propose a novel framework called Generated and Pseudo Content guided Prototype Refinement (GPCPR), which explicitly leverages LLM-generated content and reliable query context to enhance prototype quality. GPCPR achieves prototype refinement through two core components: LLM-driven Generated Content-guided Prototype Refinement (GCPR) and Pseudo Query Context-guided Prototype Refinement (PCPR). Specifically, GCPR integrates diverse and differentiated class descriptions generated by large language models to enrich prototypes with comprehensive semantic knowledge. PCPR further aggregates reliable class-specific pseudo-query context to mitigate class information bias and generate more suitable query-specific prototypes. Furthermore, we introduce a dual-distillation regularization term, enabling knowledge transfer between early-stage entities (prototypes or pseudo predictions) and their deeper counterparts to enhance refinement. Extensive experiments demonstrate the superiority of our method, surpassing the state-of-the-art methods by up to 12.10% and 13.75% mIoU on S3DIS and ScanNet, respectively.

关键词：

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：