检索结果-内蒙古大学图书馆

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Yikai Wang Wenbing Huang Yinpeng Dong Fuchun Sun Anbang Yao Department of Computer Science and Technology State Key Lab on Intelligent Technology and Systems BNRist Center Tsinghua University Gaoling School of Artificial Intelligence Renmin University of China RealAI Intel Labs China

Binary Neural Network (BNN) represents convolution weights with 1-bit values, which enhances the efficiency of storage and computation. This paper is motivated by a previously revealed phenomenon that the binary kernels in successful BNNs are nearly power-law distributed: their values are mostly clustered into a small number of codewords. This phenomenon encourages us to compact typical BNNs and obtain further close performance through learning non-repetitive kernels within a binary kernel subspace. Specifically, we regard the binarization process as kernel grouping in terms of a binary codebook, and our task lies in learning to select a smaller subset of codewords from the full code-book. We then leverage the Gumbel-Sinkhorn technique to approximate the codeword selection process, and develop the Permutation Straight-Through Estimator (PSTE) that is able to not only optimize the selection process end-to-end but also maintain the non-repetitive occupancy of selected codewords. Experiments verify that our method reduces both the model size and bit-wise computational costs, and achieves accuracy improvements compared with state-of-the-art BNNs under comparable budgets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DISCODVT: Generating Long Text with Discourse-Aware Discrete Variational Transformer

DISCODVT: Generating Long Text with Discourse-Aware Discrete...

引用

2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021

作者： Ji, Haozhe Huang, Minlie Department of Computer Science and Technology Institute for Artificial Intelligence State Key Lab of Intelligent Technology and Systems Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China

ISBN: (纸本)9781955917094

Despite the recent advances in applying pretrained language models to generate high-quality texts, generating long passages that maintain long-range coherence is yet challenging for these models. In this paper, we propose DISCODVT, a discourse-aware discrete variational Transformer to tackle the incoherence issue. DISCODVT learns a discrete variable sequence that summarizes the global structure of the text and then applies it to guide the generation process at each decoding step. To further embed discourse-aware information into the discrete latent representations, we introduce an auxiliary objective to model the discourse relations within the text. We conduct extensive experiments on two open story generation datasets and demonstrate that the latent codes learn meaningful correspondence to the discourse structures that guide the model to generate long texts with better long-range coherence. © 2021 Association for Computational Linguistics

关键词：

来源：评论

学校读者我要写书评

暂无评论

Miniature tunable Airy beam optical meta-device

引用

Opto-Electronic Advances 2024年第2期7卷 5-12页

作者： Jing Cheng Zhang Mu Ku Chen Yubin Fan Qinmiao Chen Shufan Chen Jin Yao Xiaoyuan Liu Shumin Xiao Din Ping Tsai Department of Electrical Engineering City University of Hong KongKowloonHong Kong SAR 999077China State Key Laboratory of Terahertz and Millimeter Waves City University of Hong KongKowloonHong Kong SAR 999077China Centre for Biosystems Neuroscienceand NanotechnologyCity University of Hong KongKowloonHong Kong SAR 999077China Ministry of Industry and Information Technology Key Lab of Micro-Nano Optoelectronic Information System Guangdong Provincial Key Laboratory of Semiconductor Optoelectronic Materials and Intelligent Photonic SystemsHarbin Institute of TechnologyShenzhen 518055China

Tunable Airy beams with controllable propagation trajectories have sparked interest in various fields,such as optical manipulation and laser *** research approaches encounter challenges related to insufficient compactness and integration feasibility,or they require enhanced tunability to enable real-time dynamic manipulation of the propagation *** this work,we present a novel method that utilizes a dual metasurface system to surpass these limitations,significantly enhancing the practical potential of the Airy *** approach involves encoding a cubic phase profile and two off-axis Fresnel lens phase profiles across the two *** validity of the proposed strategy has been confirmed through simulation and experimental *** proposed meta-device addresses the existing limitations and lays the foundation for broadening the applicability of Airy beams across diverse domains,encompassing light-sheet microscopy,laser fabrication,optical tweezers,etc.

关键词： metasurface miniature device tunable Airy beam tunable meta-device

来源：评论

学校读者我要写书评

暂无评论

Enhanced Large Language Models for Effective Screening of Depression and Anxiety

arXiv

引用

arXiv 2025年

作者： Liu, June M. Gao, Mengxia Sabour, Sahand Chen, Zhuang Huang, Minlie Lee, Tatia M.C. State Key Laboratory of Brain and Cognitive Sciences The University of Hong Kong Hong Kong Laboratory of Neuropsychology and Human Neuroscience The University of Hong Kong Hong Kong The CoAI group DCST Institute for Artificial Intelligence State Key Lab of Intelligent Technology and Systems Beijing National Research Center for Information Science and Technology Tsinghua University Beijing China

Depressive and anxiety disorders are widespread, necessitating timely identification and management. Recent advances in Large Language Models (LLMs) offer potential solutions, yet high costs and ethical concerns about training data remain challenges. This paper introduces a pipeline for synthesizing clinical interviews, resulting in 1,157 interactive dialogues (PsyInterview), and presents EmoScan, an LLM-based emotional disorder screening system. EmoScan distinguishes between coarse (e.g., anxiety or depressive disorders) and fine disorders (e.g., major depressive disorders) and conducts high-quality interviews. Evaluations showed that EmoScan exceeded the performance of base models and other LLMs like GPT-4 in screening emotional disorders (F1-score=0.7467). It also delivers superior explanations (BERTScore=0.9408) and demonstrates robust generalizability (F1-score of 0.67 on an external dataset). Furthermore, EmoScan outperforms baselines in interviewing skills, as validated by automated ratings and human evaluations. This work highlights the importance of scalable data-generative pipelines for developing effective mental health LLM tools. © 2025, CC BY-NC-SA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Optimal Control Based Trajectory Planning Method for Cooperative Merging Maneuvers

An Optimal Control Based Trajectory Planning Method for Coop...

引用

intelligent Robotics and systems (ISoIRS), International Symposium on

作者： Qi Wang Hao Ge Xuting Duan Jianshan Zhou State Key Lab of Intelligent Transportation System Beijing Key Laboratory for Cooperative Vehicle Infrastructure Systems and Safety Control State Key Laboratory of Air Traffic Management System and Technology School of Transportation Science and Engineering Beihang University Beijing China State Key Laboratory of Air Traffic Management System and Technology Nanjing Research Institute of Electronic Engineering Nanjing China State Key Lab of Intelligent Transportation System Beijing Key Laboratory for Cooperative Vehicle Infrastructure Systems and Safety Control School of Transportation Science and Engineering Beihang University Beijing China

Due to the prediction errors and diverse driving styles of surrounding vehicles, traffic congestion and even accidents can occur in the traffic bottleneck area where vehicles merge into the main road. To ensure that connected and automated vehicles (CAVs) can quickly and efficiently merge into the main road, this paper proposes a cooperative trajectory planning method based on optimal control for vehicle cut-in scenarios. A optimal control model is constructed, and a quintic polynomial is used to generate the initial solution of the optimal control problem to accelerate the solution process and improve the success rate. Finally, The obtained merging trajectory is then synchronized with the movement of vehicles on the main road to optimize their actions and ensure a safe merging process. Joint simulation with Robot Operating System (ROS) and RVIZ is utilized, and the results show that the proposed algorithm can quickly obtain cooperative results, the locally successful merging trajectory meets the requirements of smoothness and safety, and if the solution does not allow merging, the merging vehicle is instructed to terminate the execution.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Reinforcement Learning Algorithm for Underwater Environment Search 2

A Reinforcement Learning Algorithm for Underwater Environmen...

引用

2022 2nd International Conference on Artificial Intelligence, Big Data and Algorithms, CAIBDA 2022

作者： Xiong, Minglei Xie, Guangming State Key Laboratory for Turbulence and Complex Systems Intelligent Biomimetic Design Lab. College of Engineering Peking University Beijing100871 China Peng Cheng Laboratory Shenzhen518055 China Robot Technology Co. Ltd. Beijing100176 China

ISBN: (纸本)9783800760268

Known as an intelligent learning algorithm that can be employed without any sufficient prior information, the reinforcement learning algorithm has been widely used recently. The underwater unknown 3D environment search is a typical application scenario lacking any prior knowledge. This study proposes an algorithm framework including one agent and an intelligent swarm based on the idea of reinforcement learning. This learning algorithm can be adopted to train only one individual. Many of such individuals will then create an intelligent group which can efficiently and completely search underwater unknown 3D environments. Moreover, the proposed algorithm needs no further prior knowledge of the unknown environment. Even if the algorithm fails to reach the optimal level in the use of reinforcement learning, the results confirm the applicability prospect of reinforcement learning in this field and provide an appealing direction. © VDE VERLAG GMBH ∙ Berlin ∙ Offenbach.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Asynchronous Brain-Computer Interface Shared Control of Robotic Grasping

引用

Tsinghua Science and technology 2019年第3期24卷 360-370页

作者： Wenchang Zhang Fuchun Sun Hang Wu Chuanqi Tan Yuzhen Ma the Department of Computer Science and Technology Tsinghua University State Key Lab.of Intelligent Technology and Systems Institute of Medical Support Technology Academy of Military Sciences Drugs Control of PAP

The control of a high Degree of Freedom(DoF) robot to grasp a target in three-dimensional space using Brain-Computer Interface(BCI) remains a very difficult problem to solve. Design of synchronous BCI requires the user perform the brain activity task all the time according to the predefined paradigm; such a process is boring and fatiguing. Furthermore, the strategy of switching between robotic auto-control and BCI control is not very reliable because the accuracy of Motor Imagery(MI) pattern recognition rarely reaches 100%. In this paper, an asynchronous BCI shared control method is proposed for the high DoF robotic grasping task. The proposed method combines BCI control and automatic robotic control to simultaneously consider the robotic vision feedback and revise the unreasonable control commands. The user can easily mentally control the system and is only required to intervene and send brain commands to the automatic control system at the appropriate time according to the experience of the user. Two experiments are designed to validate our method: one aims to illustrate the accuracy of MI pattern recognition of our asynchronous BCI system; the other is the online practical experiment that controls the robot to grasp a target while avoiding an obstacle using the asynchronous BCI shared control method that can improve the safety and robustness of our system.

关键词： asynchronous Brain-Computer Interface (BCI) shared control motor imagery robotic grasping

来源：评论

学校读者我要写书评

暂无评论

Driving Performance Analysis for Connected Vehicle Platoons: Velocity Perturbation and Fuel Consumption

Driving Performance Analysis for Connected Vehicle Platoons:...

引用

IEEE International Conference on Unmanned systems (ICUS)

作者： Yihan Zhao Xuting Duan Jianshan Zhou Long Zhang State Key Lab of Intelligent Transportation System Beijing Key Laboratory for Cooperative Vehicle Infrastructure Systems and Safety Control School of Transportation Science and Engineering Beihang University Beijing China State Key Lab of Intelligent Transportation System Beijing Key Laboratory for Cooperative Vehicle Infrastructure Systems and Safety Control Zhongguancun Laboratory School of Transportation Science and Engineering Beihang University Beijing China National Key Laboratory of Science and Technology on Information System Security Institute of Systems Engineering Beijing China

Vehicle platoon is one of the concrete manifestations of multi-vehicle cooperative control and intelligent transportation. However, the velocity perturbation in the driving process will bring about stability and safety problems. The connected autonomous vehicles (CAVs) can obtain the motion status of the lead vehicle in real time and respond to it in time, which is of far-reaching significance to platoon control. Based on this, this paper focuses on the longitudinal driving strategy of connected autonomous vehicle platoons. Specifically, we provide a discrete double-integral model controller for each vehicle in a generic scenario, and the controller performs acceleration and deceleration control at each timeslot according to the state of the vehicle in front and its own state. Simulation experiments are designed by varying the size of the platoon and the number of connected autonomous vehicles. The experimental results show that the introduction of connected autonomous vehicles can effectively suppress the platoon velocity perturbation, increase the stability of the platoon driving, and significantly reduce the fuel consumption at the same time.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Domain Adaptation Regression for Force Calibration of Optical Tactile Sensors

Deep Domain Adaptation Regression for Force Calibration of O...

引用

IEEE/RSJ International Conference on intelligent Robots and systems (IROS)

作者： Zhuo Chen Ni Ou Jiaqi Jiang Shan Luo Department of Engineering Robot Perception Lab Centre for Robotics Research King’s College London London United Kingdom State Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing Institute of Technology Beijing China

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Optical tactile sensors provide robots with rich force information for robot grasping in unstructured environments. The fast and accurate calibration of three-dimensional contact forces holds significance for new sensors and existing tactile sensors which may have incurred damage or aging. However, the conventional neural-network-based force calibration method necessitates a large volume of force-labeled tactile images to minimize force prediction errors, with the need for accurate Force/Torque measurement tools as well as a time-consuming data collection process. To address this challenge, we propose a novel deep domain-adaptation force calibration method, designed to transfer the force prediction ability from a calibrated optical tactile sensor to uncalibrated ones with various combinations of domain gaps, including marker presence, illumination condition, and elastomer modulus. Experimental results show the effectiveness of the proposed unsupervised force calibration method, with lowest force prediction errors of 0.102N (3.4% in full force range) for normal force, and 0.095N (6.3%) and 0.062N (4.1%) for shear forces along the x-axis and y-axis, respectively. This study presents a promising, general force calibration methodology for optical tactile sensors.

关键词： Accuracy Force Tactile sensors Lighting Elastomers Data collection Optical imaging Adaptive optics Calibration Optical sensors

来源：评论

学校读者我要写书评

暂无评论

Pre-Training to Learn in Context

arXiv

引用

arXiv 2023年

作者： Gu, Yuxian Dong, Li Wei, Furu Huang, Minlie The CoAI Group DCST Institute for Artificial Intelligence State Key Lab of Intelligent Technology and Systems Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China Microsoft Research

In-context learning, where pre-trained language models learn to perform tasks from task examples and instructions in their contexts, has attracted much attention in the NLP community. However, the ability of in-context learning is not fully exploited because language models are not explicitly trained to learn in context. To this end, we propose PICL (Pre-training for In-Context Learning), a framework to enhance the language models' in-context learning ability by pre-training the model on a large collection of "intrinsic tasks" in the general plain-text corpus using the simple language modeling objective. PICL encourages the model to infer and perform tasks by conditioning on the contexts while maintaining task generalization of pre-trained models. We evaluate the in-context learning performance of the model trained with PICL on seven widely-used text classification datasets and the SUPERNATURALINSTRCTIONS benchmark, which contains 100+ NLP tasks formulated to text generation. Our experiments show that PICL is more effective and task-generalizable than a range of baselines, outperforming larger language models with nearly 4x parameters. The code is publicly available at https://***/thu-coai/PICL. © 2023, CC BY.

关键词： Natural language processing systems

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：