检索结果-内蒙古大学图书馆

Self-prompted Chain-of-Thought on Large Language Models for Open-domain Multi-hop Reasoning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Jinyuan Li, Junlong Zhao, Hai SJTU-Paris Elite Institute of Technology Shanghai Jiao Tong University China Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University China

In open-domain question-answering (ODQA), most existing questions require single-hop reasoning on commonsense. To further extend this task, we officially introduce open-domain multi-hop reasoning (ODMR) by answering multi-hop questions with explicit reasoning steps in open-domain setting. Recently, large language models (LLMs) have found significant utility in facilitating ODQA without external corpus. Furthermore, chain-of-thought (CoT) prompting boosts the reasoning capability of LLMs to a greater extent with manual or automated paradigms. However, existing automated methods lack of quality assurance, while manual approaches suffer from limited scalability and poor diversity, hindering the capabilities of LLMs. In this paper, we propose Self-prompted Chain-of-Thought (SP-CoT), an automated framework to mass-produce high quality CoTs of LLMs, by LLMs and for LLMs. SP-CoT introduces an automated generation pipeline of high quality ODMR datasets, an adaptive sampler for in-context CoT selection and self-prompted inference via in-context learning. Extensive experiments on four multi-hop question-answering benchmarks show that our proposed SP-CoT not only significantly surpasses the previous SOTA methods on large-scale (175B) LLMs, but also nearly doubles the zero-shot performance of small-scale (13B) LLMs. Further analysis reveals the remarkable capability of SP-CoT to elicit direct and concise intermediate reasoning steps by recalling ∼50% of intermediate answers on MuSiQue-Ans dataset. Copyright © 2023, The Authors. All rights reserved.

关键词： Benchmarking

Camera-Based HRV Prediction for Remote Learning Environments

学校读者我要写书评

暂无评论

Camera-Based HRV Prediction for Remote Learning Environments

Smart World Congress (SWC), IEEE

作者： Kegang Wang Yantao Wei Jiankai Tang Yuntao Wang Zhe Li Mingwen Tong Jie Gao Yujian Ma Zhongjin Zhao Central China Normal University Wuhan China Department of Computer Science and Technology Tsinghua University Beijing China National Key Laboratory of Human Factors Engineering Beijing China Ant Group Beijing China East China Normal University Shanghai China

ISBN: (数字)9798331520861

ISBN: (纸本)9798331520878

In recent years, the widespread use of online facial videos has brought increasing attention to remote photoplethys-mography (rPPG) in affective computing. Recovering blood volume pulse (BVP) signals from facial videos is a complex task, involving multiple stages of preprocessing, image analysis, and postprocessing to accurately reconstruct waveforms. Not only is the heart rate metric utilized for affective computing, but the heart rate variability (HRV) metric is even more significant. The challenge in obtaining HRV indices through rPPG lies in the necessity for algorithms to precisely predict the BVP peak positions. In this paper, we collected the Remote Learning Affect and Physiology (RLAP) dataset, which includes over 32 hours of highly synchronized video and labels from 58 subjects. This is a public dataset whose BVP labels have been meticulously designed to better suit the training of HRV models. Using the RLAP dataset, we trained a new model called Seq-rPPG, it is a model based on one-dimensional convolution, and experimental results reveal that this structure is more suitable for handling HRV tasks, which outperformed all other baselines in HRV performance and also demonstrated significant advantages in computational efficiency. The RLAP dataset is open source: https://***/KegangWangCCNU/RLAP-dataset

关键词： Training Affective computing Distance learning Computational modeling Prediction algorithms Real-time systems Physiology Synchronization Heart rate variability Videos

Learning Time-Series Images of Niacin Skin-Flushing Test for the Diagnosis of Schizophrenia and Affective Disorder

学校读者我要写书评

暂无评论

Learning Time-Series Images of Niacin Skin-Flushing Test for...

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Huang, Yuyang Dong, Shiwen Wang, Dandan Wan, Chunling Yang, Yang Shanghai Jiao Tong University Department of Computer Science and Engineering Shanghai China Shanghai Jiao Tong University Department of Electronic Engineering Shanghai China Bio-X Institutes Key Laboratory for the Genetics of Developmental and Neuropsychiatric Disorders Ministry of Education Shanghai Jiao Tong University Shanghai200030 China Key Lab. of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai200240 China

ISBN: (纸本)9781665468190

Niacin skin-flushing test is a promising method for fast and objective diagnosis of schizophrenia and affective disorder. Compared to healthy controls, the patients have attenuated flushing extent and reduced flushing rate. The traditional analysis of niacin test relies on manually evaluated flushing extent, while flushing patterns sh own in the sk in test images have not yet been considered. To exploit the potential of raw images for diagnosis and avoid subjective and time-consuming estimation of the flushing levels, we propose a CNN-LSTM hybrid model to learn the time-series of images captured in the niacin skin-flushing test. Moreover, an attention layer is introduced to enhance the model performance and interpretability. We collect a data set of 796 participants, and the experimental results show that the new model outperforms the traditional 4-point scaled measurement and conventional deep learning methods by large margins. Besides, the attention scores yielded by the model reveals key time points during the flushing reaction. © 2022 IEEE.

关键词： Time series

SKU-Patch: Towards Efficient Instance Segmentation for Unseen Objects in Auto-Store

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Yang, Biqi Tang, Weiliang Gao, Xiaojie Li, Xianzhi Liu, Yun-Hui Fu, Chi-Wing Heng, Pheng-Ann The Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China The School of Computer Science and Technology Huazhong University of Science and Technology China The Department of Mechanical and Automation Engineering The Chinese University of Hong Kong Hong Kong

In large-scale storehouses, precise instance masks are crucial for robotic bin picking but are challenging to obtain. Existing instance segmentation methods typically rely on a tedious process of scene collection, mask annotation, and network fine-tuning for every single Stock Keeping Unit (SKU). This paper presents SKU-Patch, a new patch-guided instance segmentation solution, leveraging only a few image patches for each incoming new SKU to predict accurate and robust masks, without tedious manual effort and model re-training. Technical-wise, we design a novel transformer-based network with (i) a patch-image correlation encoder to capture multi-level image features calibrated by patch information and (ii) a patch-aware transformer decoder with parallel task heads to generate instance masks. Extensive experiments on four storehouse benchmarks manifest that SKU-Patch is able to achieve the best performance over the state-of-the-art methods. Also, SKU-Patch yields an average of nearly 100% grasping success rate on more than 50 unseen SKUs in a robot-aided auto-store logistic pipeline, showing its effectiveness and practicality. Copyright © 2023, The Authors. All rights reserved.

关键词： Benchmarking

Mitigating Misleading Chain-of-Thought Reasoning with Selective Filtering

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wu, Yexin Zhang, Zhuosheng Zhao, Hai College of Zhiyuan Shanghai Jiao Tong University China School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University China Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University China

Large language models have manifested remarkable capabilities by leveraging chain-of-thought (CoT) reasoning techniques to solve intricate questions through step-by-step reasoning chains. Despite its success, the efficacy of such reasoning is inherently contingent upon the quality of CoT. However, flawless CoT reasoning cannot be guaranteed due to the presence of indecomposable questions and the potential for erroneous reasoning chains, particularly in the case of small-scale language models. To tackle this challenge, we propose a novel approach called the selective filtering reasoner (SelF-Reasoner) that assesses the entailment relationship between the question and the candidate reasoning chain. Then, we proceed with CoT reasoning when the reasoning chain demonstrates confidence;otherwise, we opt to predict the answer directly. SelF-Reasoner improves the fine-tuned T5 baseline consistently over the scienceQA, ECQA, and LastLetter tasks. Code is available at https://***/LibroWu/SelF-Reasoner. © 2024, CC BY-SA.

关键词： Computational linguistics

Incorporating simulated spatial context information improves the effectiveness of contrastive learning models

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhu, Lizhen Wang, James Z. Lee, Wonseuk Wyble, Brad Data Science and Artificial Intelligence Area College of Information Sciences and Technology The Pennsylvania State University University ParkPA United States Human-Computer Interaction Area College of Information Sciences and Technology The Pennsylvania State University University ParkPA United States Department of Communication and Media School of Social Sciences and Humanities Loughborough University Leicestershire Loughborough United Kingdom Department of Computer Science and Engineering The Pennsylvania State University University ParkPA United States Department of Psychology The Pennsylvania State University University ParkPA United States

Visual learning often occurs in a specific context, where an agent acquires skills through exploration and tracking of its location in a consistent environment. The historical spatial context of the agent provides a similarity signal for self-supervised contrastive learning. We present a unique approach, termed Environmental Spatial Similarity (ESS), that complements existing contrastive learning methods. Using images from simulated, photorealistic environments as an experimental setting, we demonstrate that ESS outperforms traditional instance discrimination approaches. Moreover, sampling additional data from the same environment substantially improves accuracy and provides new augmentations. ESS allows remarkable proficiency in room classification and spatial prediction tasks, especially in unfamiliar environments. This learning paradigm has the potential to enable rapid visual learning in agents operating in new environments with unique visual characteristics. Potentially transformative applications span from robotics to space exploration. Our proof of concept demonstrates improved efficiency over methods that rely on extensive, disconnected datasets. Copyright © 2024, The Authors. All rights reserved.

关键词： computer vision

A human-human Physical interaction System for Training Handwriting

学校读者我要写书评

暂无评论

A Human-Human Physical Interaction System for Training Handw...

IEEE/RAS-EMBS International Conference on Biomedical Robotics and Biomechatronics (BioRob)

作者： S. Buscaglione A. Noccaro C. Provenzale C. Bonsignori E. Ivanova L. Sparaci F. Taffoni E. Burdet D. Formica NEXT: Neurophysiology and Neuroengineering of Human-Technology Interaction Research Unit Università Campus Bio-Medico di Roma Italy Neurorobotics Lab Newcastle University Newcastle Upon Tyne UK Advanced Robotics and Human-Centred Technologies-CREO Laboratory Università Campus Bio-Medico di Roma Italy Department of Bioengineering Imperial College of Science Technology and Medicine UK School of Electric Engineering and Computer Science Queen Mary University of London UK Institute of Cognitive Sciences and Technologies (ISTC) National Research Council of Italy (CNR) Italy

ISBN: (数字)9798350386523

ISBN: (纸本)9798350386530

Handwriting training in childhood is known to influence academic success, foster self-esteem, and contribute to overall development. Previous studies underscored the positive impact of haptic feedback on handwriting learning using one-way communication systems that provided the trainee with haptic feedback based on pre-recorded trainer's movements. In this study, we propose a system involving bidirectional physical coupling (haptic communication) between a trainee and a trainer to exploit the advantages of haptic communication for motor task improvement, proved in tracking tasks. The system, composed of an interactive display and a coupling spring, was tested in a handwriting task performed by a dyad of healthy adults with different cursive handwriting backgrounds. The participants' performance demonstrated the feasibility of using this system for handwriting, opening the way for further studies to assess its benefits in handwriting improvement and learning.

关键词： Training Couplings Tracking Communication systems Biomechatronics Motors Haptic interfaces Springs Robots

Efficiently Fusing Sparse Lidar for Enhanced Self-Supervised Monocular Depth Estimation

学校读者我要写书评

暂无评论

Efficiently Fusing Sparse Lidar for Enhanced Self-Supervised...

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

作者： Yue Wang Mingrong Gong Lei Xia Qieshi Zhang Jun Cheng Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China Department of Computer Science University College London UK

Monocular self-supervised depth estimation with a low-cost sensor is the mainstream solution to gathering dense depth maps for robots and autonomous driving. In this paper, based on the philosophy "less is more" (i.e., focusing only on valid pixels in sparse LiDAR), we propose a novel framework, Efficient Sparse Depth (EffisDepth), for predicting dense depth. The Sparse Feature Extractor (SFE) embedded in the proposed framework effectively handles sparse LiDAR by forming sparse tensors. The Slender Group Block (SGB) is the main building block in SFE, which extracts features from sparse tensors via a structure of two branches. Extensive experiments show that our method achieves state-of-the-art performance on the KITTI benchmark, demonstrating the effectiveness of each proposed component and the self-supervised learning framework.

关键词： Laser radar Tensors Philosophical considerations Fuses Estimation Self-supervised learning Signal processing

PyramidInfer: Pyramid KV Cache Compression for High-throughput LLM Inference

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yang, Dongjie Han, Xiaodong Gao, Yan Hu, Yao Zhang, Shilin Zhao, Hai Shanghai Jiao Tong University China Xiaohongshu Inc. China South China University of Technology China The Department of Computer Science and Engineering Shanghai Jiao Tong University Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai Key Laboratory of Trusted Data Circulation and Governance in Web3 China

Large Language Models (LLMs) have shown remarkable comprehension abilities but face challenges in GPU memory usage during inference, hindering their scalability for real-time applications like chatbots. To accelerate inference, we store computed keys and values (KV cache) in the GPU memory. Existing methods study the KV cache compression to reduce memory by pruning the pre-computed KV cache. However, they neglect the inter-layer dependency between layers and huge memory consumption in pre-computation. To explore these deficiencies, we find that the number of crucial keys and values that influence future generations decreases layer by layer and we can extract them by the consistency in attention weights. Based on the findings, we propose PyramidInfer, a method that compresses the KV cache by layer-wise retaining crucial context. PyramidInfer saves significant memory by computing fewer keys and values without sacrificing performance. Experimental results show PyramidInfer improves 2.2x throughput compared to Accelerate with over 54% GPU memory reduction in KV cache. Our code is available in https://***/mutonix/ pyramidinfer. © 2024, CC BY.

关键词： Cache memory