检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Yang, Dingkang Wei, Jinjie Xiao, Dongling Wang, Shunli Wu, Tong Li, Gang Li, Mingcheng Wang, Shuaibing Chen, Jiawei Jiang, Yue Xu, Qingyao Li, Ke Zhai, Peng Zhang, Lihua Academy for Engineering and Technology Fudan University Shanghai China Tencent Youtu Lab Shanghai China Cognition and Intelligent Technology Laboratory Shanghai China Engineering Research Center of AI and Robotics Ministry of Education Shanghai China AI and Unmanned Systems Engineering Research Center of Jilin Province Changchun China

Developing intelligent pediatric consultation systems offers promising prospects for improving diagnostic efficiency, especially in China, where healthcare resources are scarce. Despite recent advances in Large Language Models (LLMs) for Chinese medicine, their performance is sub-optimal in pediatric applications due to inadequate instruction data and vulnerable training procedures. To address the above issues, this paper builds PedCorpus, a high-quality dataset of over 300,000 multi-task instructions from pediatric textbooks, guidelines, and knowledge graph resources to fulfil diverse diagnostic demands. Upon well-designed PedCorpus, we propose PediatricsGPT, the first Chinese pediatric LLM assistant built on a systematic and robust training pipeline. In the continuous pre-training phase, we introduce a hybrid instruction pre-training mechanism to mitigate the internal-injected knowledge inconsistency of LLMs for medical domain adaptation. Immediately, the full-parameter Supervised Fine-Tuning (SFT) is utilized to incorporate the general medical knowledge schema into the models. After that, we devise a direct following preference optimization to enhance the generation of pediatrician-like humanistic responses. In the parameter-efficient secondary SFT phase, a mixture of universal-specific experts strategy is presented to resolve the competency conflict between medical generalist and pediatric expertise mastery. Extensive results based on the metrics, GPT-4, and doctor evaluations on distinct downstream tasks show that PediatricsGPT consistently outperforms previous Chinese medical LLMs. The project and data will be released at https://***/ydk122024/PediatricsGPT. Copyright © 2024, The Authors. All rights reserved.

关键词： Pediatrics

来源：评论

学校读者我要写书评

暂无评论

Marker or Markerless? Mode-Switchable Optical Tactile Sensing for Diverse Robot Tasks

arXiv

引用

arXiv 2024年

作者： Ou, Ni Chen, Zhuo Luo, Shan The State Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing Institute of Technology Beijing100081 China The Robot Perception Lab. Centre for Robotics Research Department of Engineering King’s College London LondonWC2R 2LS United Kingdom

Optical tactile sensors play a pivotal role in robot perception and manipulation tasks. The membrane of these sensors can be painted with markers or remain markerless, enabling them to function in either marker or markerless mode. However, this uni-modal selection means the sensor is only suitable for either manipulation or perception tasks. While markers are vital for manipulation, they can also obstruct the camera, thereby impeding perception. The dilemma of selecting between marker and markerless modes presents a significant obstacle. To address this issue, we propose a novel mode-switchable optical tactile sensing approach that facilitates transitions between the two modes. The marker-to-markerless transition is achieved through a generative model, whereas its inverse transition is realized using a sparsely supervised regressive model. Our approach allows a single-mode optical sensor to operate effectively in both marker and markerless modes without the need for additional hardware, making it well-suited for both perception and manipulation tasks. Extensive experiments validate the effectiveness of our method. For perception tasks, our approach decreases the number of categories that include misclassified samples by 2 and improves contact area segmentation IoU by 3.53%. For manipulation tasks, our method attains a high success rate of 92.59% in slip detection. Code, dataset and demo videos are available at the project website https://***/Marker-Markerless-Transition/ Copyright © 2024, The Authors. All rights reserved.

关键词： Tactile sensors

来源：评论

学校读者我要写书评

暂无评论

Detecting and Evaluating Medical Hallucinations in Large Vision Language Models

arXiv

引用

arXiv 2024年

作者： Chen, Jiawei Yang, Dingkang Wu, Tong Jiang, Yue Hou, Xiaolu Li, Mingcheng Wang, Shunli Xiao, Dongling Li, Ke Zhang, Lihua Academy for Engineering and Technology Fudan University Shanghai China Tencent Youtu Lab Shanghai China Cognition and Intelligent Technology Laboratory Shanghai China Engineering Research Center of AI and Robotics Ministry of Education Shanghai China AI and Unmanned Systems Engineering Research Center of Jilin Province Changchun China

Large Vision Language Models (LVLMs) are increasingly integral to healthcare applications, including medical visual question answering and imaging report generation. While these models inherit the robust capabilities of foundational Large Language Models (LLMs), they also inherit susceptibility to hallucinations-a significant concern in high-stakes medical contexts where the margin for error is minimal. However, currently, there are no dedicated methods or benchmarks for hallucination detection and evaluation in the medical field. To bridge this gap, we introduce Med-HallMark, the first benchmark specifically designed for hallucination detection and evaluation within the medical multimodal domain. This benchmark provides multi-tasking hallucination support, multifaceted hallucination data, and hierarchical hallucination categorization. Furthermore, we propose the MediHall Score, a new medical evaluative metric designed to assess LVLMs' hallucinations through a hierarchical scoring system that considers the severity and type of hallucination, thereby enabling a granular assessment of potential clinical impacts. We also present MediHallDetector, a novel Medical LVLM engineered for precise hallucination detection, which employs multitask training for hallucination detection. Through extensive experimental evaluations, we establish baselines for popular LVLMs using our benchmark. The findings indicate that MediHall Score provides a more nuanced understanding of hallucination impacts compared to traditional metrics and demonstrate the enhanced performance of MediHallDetector. We hope this work can significantly improve the reliability of LVLMs in medical applications. All resources of this work will be released soon. Copyright © 2024, The Authors. All rights reserved.

关键词： Medical applications

来源：评论

学校读者我要写书评

暂无评论

6DoF-ICTC: A Deep Image Feature Extraction Network Combining Transformers and CNNs for 6DoF Pose Estimation 12

6DoF-ICTC: A Deep Image Feature Extraction Network Combining...

引用

12th International Conference on CYBER Technology in Automation, Control, and intelligent systems, CYBER 2022

作者： Zhang, Liming Zhou, Xin Zhu, Baixian Wang, Can Wu, Xinyu Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China Cas Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology China University of Science and Technology of China China Department of Mechanical and Automation Engineering The Chinese University of Hong Kong Hong Kong

ISBN: (数字)9781665472678

ISBN: (纸本)9781665472678

In this work, we propose a new image feature extraction network for 6D pose estimation tasks. The majority of existing 6D pose estimation networks are based on the RGBD input, which is the fusion of images and point clouds. They are mainly working on keypoint extraction, point cloud feature extraction, and other tasks, however, image features, on the other hand, mainly rely on CNN networks that are currently advanced. With the development of Vision Transformer in the field of computer vision, the results on ImageNet demonstrate its benefit of extracting global features, and we see new directions that the Transformers can bring to the area of image feature extraction. ICTC is a Transformer paired with a CNN network that fuses the retrieved global features into each pixel and then does local feature extraction. This provides greater robustness to 6D pose estimation In complex situations such as shifting lighting conditions and object occlusion. Our method achieves 96% accuracy using the average ADD metric on the LineMOD dataset, demonstrating our method's effectiveness. © 2022 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Plan-based relaxed reward shaping for goal-directed tasks

arXiv

引用

arXiv 2021年

作者： Schubert, Ingmar Oguz, Ozgur S. Toussaint, Marc Learning and Intelligent Systems Group TU Berlin Germany Max Planck Institute for Intelligent Systems Stuttgart Germany Machine Learning and Robotics Lab University of Stuttgart Germany

In high-dimensional state spaces, the usefulness of Reinforcement Learning (RL) is limited by the problem of exploration. This issue has been addressed using potential-based reward shaping (PB-RS) previously. In the present work, we introduce Final-Volume-Preserving Reward Shaping (FV-RS). FV-RS relaxes the strict optimality guarantees of PB-RS to a guarantee of preserved long-term behavior. Being less restrictive, FV-RS allows for reward shaping functions that are even better suited for improving the sample efficiency of RL algorithms. In particular, we consider settings in which the agent has access to an approximate plan. Here, we use examples of simulated robotic manipulation tasks to demonstrate that plan-based FV-RS can indeed significantly improve the sample efficiency of RL over plan-based PB-RS. © 2021, CC BY.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Uncovering the Interpretation of Large Language Models

Uncovering the Interpretation of Large Language Models

引用

IEEE Annual International Computer Software and Applications Conference (COMPSAC)

作者： Mst Shapna Akter Hossain Shahriar Alfredo Cuzzocrea Fan Wu Dept. of Intelligent and Robotics Systems University of West Florida USA Center for Cyberxecurity University of West Florida USA iDEA Lab University of Calabria Rende Italy Dept. of Computer Science University of Paris City Paris France Dept. of Computer Science Tuskegee University Tuskegee USA

ISBN: (数字)9798350376968

ISBN: (纸本)9798350376975

Recent research has shown growing interest in the arithmetic reasoning capabilities of large language models (LLMs), especially those built on the Transformer architecture. However, our understanding of the intrinsic processes within these models for arithmetic calculations remains scant. This study leverages causal mediation analysis to offer an in-depth look at how Transformer-based LLMs approach complex arithmetic problems. We experimentally intervened on particular model activations and assessed the resulting shifts in prediction probabilities, allowing us to pinpoint which parameters are crucial for such reasoning tasks. We discovered that for complex arithmetic operations, information is channeled from mid-layer activations to the final token through enhanced attention mechanisms. Subsequently, Multi-Layer Perceptrons (MLP) modules synthesize this data, integrating it into the model's residual pathways. To validate these observations, we also evaluated the activation dynamics across different types of tasks, such as retrieving numbers from text and answering fact-based questions.

关键词： Computational modeling Large language models Predictive models Transformers Mathematical models Data models Cognition

来源：评论

学校读者我要写书评

暂无评论

Quantum Adversarial Attacks: Developing Quantum FGSM Algorithm

Quantum Adversarial Attacks: Developing Quantum FGSM Algorit...

引用

IEEE Annual International Computer Software and Applications Conference (COMPSAC)

作者： Mst Shapna Akter Hossain Shahriar Alfredo Cuzzocrea Fan Wu Dept. of Intelligent and Robotics Systems University of West Florida USA Center for CyberSecurity University of West Florida USA iDEA Lab University of Calabria Rende Italy Dept. of Computer Science University of Paris City Paris France Dept. of Computer Science Tuskegee University Tuskegee USA

ISBN: (数字)9798350376968

ISBN: (纸本)9798350376975

Quantum machine learning, noted for its remarkable advancements in enhancing computational speed and augmenting data processing efficacy, is acquiring considerable recognition within the scientific community. Despite the noteworthy advancements of quantum machine learning, it shares with its traditional counterpart a susceptibility to adversarial threats. This presents a significant challenge and underscores the need for robust countermeasures in this emerging field of study. Developing effective adversarial attack algorithms, such as the Quantum Fast Gradient Sign Method (QFGSM), is crucial to opening the path for exploring robust defense mechanisms against these threats. However, unlike traditional machine learning, the quantum field currently lacks the effective techniques to orchestrate adversarial attacks. This study introduces and assesses the QFGSM, a adversarial attack algorithm tailored for QNNs. Additionally, we evaluate the effect of random noise and its quantum version on these models, providing a comprehensive comparison to understand the efficacy of adversarial attack methods. The evaluation is conducted on both traditional Neural Networks (NNs) and QNNs using the ClaMP dataset, a cybersecurity-focused dataset, and involves performance metrics like Accuracy, Precision, Recall, and F1 score. Our findings underscore the differential resilience of NNs and QNNs under adversarial attacks and reveal the contrasting effects of FGSM, QFGSM, and random noise-based methods. Our study reveals that Quantum Neural Networks (QNNs) show significant vulnerability to our proposed Quantum Fast Gradient Sign Method (QFGSM) compared to random noise, indicating a need for quantum-specific defenses in the face of this advanced adversarial attack algorithm.

关键词： Measurement Quantum computing Machine learning algorithms Accuracy Noise Machine learning Artificial neural networks

来源：评论

学校读者我要写书评

暂无评论

The Stiffness of 3-PRS PM Across Parasitic and Orientational Workspace

The Stiffness of 3-PRS PM Across Parasitic and Orientational...

引用

ASME/IFToMM International Conference on Reconfigurable Mechanisms and Robots, ReMAR

作者： Hassen Nigatu Li Jihao Keqi Zhu Junhan Zhang Haotian Guo Guodong Lu Doik Kim Robot Perception and Grasp Lab School of Mechanical Engineering Zhejiang University Hangzhou China Robotics Research Center of Yuyao Yuyao Technology Innovation Center Robotics Institute of Zhejiang University Ningbo Shi Zhejiang Province China The State Key Laboratory of Fluid Power and Mechatronic Systems and the Engineering Research Center for Design Engineering and Digital Twin of Zhejiang Province School of Mechanical Engineering School of Mechanical Engineering Zhejiang University Hangzhou China xR Lab Center for Intelligent and Interactive Robotics Artificial Intelligence and Robot Institute Korea Institute of Science and Technology (KIST) South Korea

ISBN: (数字)9798350395969

ISBN: (纸本)9798350395976

This study investigates the stiffness characteristics of the Sprint Z3 head, also known as 3- PRS Parallel Kinematics Machines, which are among the most extensively researched and viably successful manipulators for precision machining applications. Despite the wealth of research on these robotic manipulators, no previous work has demonstrated their stiffness performance within the parasitic motion space. Such an undesired motion influences their stiffness properties, as stiffness is configuration-dependent. Addressing this gap, this paper develops a stiffness model that accounts for both the velocity-level parasitic motion space and the regular workspace. Numerical simulations are provided to illustrate the stiffness characteristics of the manipulator across all considered spaces. The results indicate that the stiffness profile within the parasitic motion space is both shallower and the values are smaller when compared to the stiffness distribution across the orientation workspace. This implies that evaluating a manipulator's performance adequately requires assessing its ability to resist external loads during parasitic motion. Therefore, comprehending this aspect is crucial for redesigning components to enhance overall stiffness.

关键词： Simulation Resists Machining Kinematics Manipulators Numerical simulation Magnetic heads

来源：评论

学校读者我要写书评

暂无评论

Learning to arbitrate human and robot control using disagreement between sub-policies

arXiv

引用

arXiv 2021年

作者： Oh, Yoojin Toussaint, Marc Mainprice, Jim Machine Learning and Robotics Lab University of Stuttgart Germany Learning and Intelligent Systems Lab TU Berlin Berlin Germany Max Planck Institute for Intelligent Systems MPI-IS Tübingen/Stuttgart Germany

In the context of teleoperation, arbitration refers to deciding how to blend between human and autonomous robot commands. We present a reinforcement learning solution that learns an optimal arbitration strategy that allocates more control authority to the human when the robot comes across a decision point in the task. A decision point is where the robot encounters multiple options (sub-policies), such as having multiple paths to get around an obstacle or deciding between two candidate goals. By expressing each directional sub-policy as a von Mises distribution, we identify the decision points by observing the modality of the mixture distribution. Our reward function reasons on this modality and prioritizes to match its learned policy to either the user or the robot accordingly. We report teleoperation experiments on reach-and-grasping objects using a robot manipulator arm with different simulated human controllers. Results indicate that our shared control agent outperforms direct control and improves the teleoperation performance among different users. Using our reward term enables flexible blending between human and robot commands while maintaining safe and accurate teleoperation. Copyright © 2021, The Authors. All rights reserved.

关键词： Remote control

来源：评论

学校读者我要写书评

暂无评论

Deep 6-DoF tracking of unknown objects for reactive grasping

arXiv

引用

arXiv 2021年

作者： Tuscher, Marc Hörz, Julian Driess, Danny Toussaint, Marc Sereact Germany Machine Learning and Robotics Lab University of Stuttgart Germany Max-Planck Institute for Intelligent Systems Stuttgart Germany Learning and Intelligent Systems TU Berlin Germany

Robotic manipulation of unknown objects is an important field of research. Practical applications occur in many real-world settings where robots need to interact with an unknown environment. We tackle the problem of reactive grasping by proposing a method for unknown object tracking, grasp point sampling and dynamic trajectory planning. Our object tracking method combines Siamese Networks with an Iterative Closest Point approach for pointcloud registration into a method for 6-DoF unknown object tracking. The method does not require further training and is robust to noise and occlusion. We propose a robotic manipulation system, which is able to grasp a wide variety of formerly unseen objects and is robust against object perturbations and inferior grasping points. © 2021, CC BY.

关键词： Iterative 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：