检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Gui, Shangtong Shao, Chenze Ma, Zhengrui Zhang, Xishan Chen, Yunji Feng, Yang State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China Cambricon Technologies China

Non-autoregressive Transformer(NAT) significantly accelerates the inference of neural machine translation. However, conventional NAT models suffer from limited expression power and performance degradation compared to autoregressive (AT) models due to the assumption of conditional independence among target tokens. To address these limitations, we propose a novel approach called PCFG-NAT, which leverages a specially designed Probabilistic Context-Free Grammar (PCFG) to enhance the ability of NAT models to capture complex dependencies among output tokens. Experimental results on major machine translation benchmarks demonstrate that PCFG-NAT further narrows the gap in translation quality between NAT and AT models. Moreover, PCFG-NAT facilitates a deeper understanding of the generated sentences, addressing the lack of satisfactory explainability in neural machine translation.2 Copyright © 2023, The Authors. All rights reserved.

关键词： Computer aided language translation

来源：评论

学校读者我要写书评

暂无评论

FoodSky: A Food-Oriented Large Language Model Can Pass the Chef and Dietetic Examination

SSRN

引用

SSRN 2024年

作者： Zhou, Pengfei Min, Weiqing Fu, Chaoran Jin, Ying Huang, Mingyu Li, Xiangyang Mei, Shuhuan Jiang, Shuqiang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Institute of Intelligent Computing Technology Chinese Academy of Sciences Suzhou China Zhongke Shenjian Technology Co. Ltd. Suzhou China

Food is the cornerstone of both survival and social life. With the increasing complexity of global dietary needs and preferences, there is a growing demand for food intelligence to enable tasks like recipe recommendation and diet-disease correlation discovery. To address this, we introduce the Food-oriented Large Language Model (LLM) FoodSky, which offers fine-grained perception and reasoning of food data. We constructed a food corpus, FoodEarth, from various authoritative sources to enhance FoodSky's knowledge. We also developed the Topic-based Selective State Space Model and Hierarchical Topic Retrieval Augmented Generation algorithms to improve FoodSky's ability to capture fine-grained food semantics and generate context-aware food-relevant text. Extensive experiments show that FoodSky outperforms general-purpose LLMs on the Chinese National Chef Exam and Dietetic Exam, achieving accuracies of 67.2% and 66.4%, respectively. FoodSky not only enhances culinary creativity and promotes healthier eating patterns but also establishes a new standard for domain-specific LLMs tackling real-world food-related issues. © 2024, The Authors. All rights reserved.

关键词： Food ingredients

来源：评论

学校读者我要写书评

暂无评论

FlyLISL: Traffic Balance Awared Routing for Large-scale Mixed-Reality Telepresence over Reconfigurable Mega-Constellation 42

FlyLISL: Traffic Balance Awared Routing for Large-scale Mixe...

引用

42nd IEEE International Conference on Distributed computing Systems Workshops, ICDCSW 2022

作者： Zhang, Ruoyi Deng, Jing Liu, Qi Xie, Xinlei Gong, Qingyuan Zhu, Chao Beijing Institute of Technology School of Cyberspace Science and Technology China Communication University of China State Key Laboratory of Media Convergence and Communication China School of Information and Electronics Beijing Institute of Technology China School of Computer Science Fudan University Shanghai Key Lab of Intelligent Information Processing China

ISBN: (数字)9781665488792

ISBN: (纸本)9781665488792

With the emerging telepresence applications, such as meta universe, tele-education and tele-social, there exist a large number of demands for sufficient network resources for visual streaming. However, transmitting the huge volume of the generated visual data through the meandering terrestrial networks would overwhelm the backbone networks and cause non-negligible latency. Mega-constellations, such as OneWeb and Starlink, is developing as one of 'New Infrastructure Construction', and could provide high-capacity and low-latency communication in a world-wide range. However, most of the existing mega-constellation networks' topology is fixed and would easily fall into congestion with the bursting traffic generated by the large-scale telepresence applications. To address this challenge, we propose a reconfigurable mega-constellation architecture by utilizing the permanent and temporary laser inter-satellite links (LISLs). Moreover, based on the mixed-integer linear programming (MILP), we design a routing system, FlyLISL, aiming at balancing the global traffic load by minimizing the maximum link utilization of all LISLs. To evaluate the effectiveness of FlyLISL, we simulate the performance of FlyLISL by comparing with the particle swarm optimization (PSO) and Random based routing strategies. Compared with reference works, FlyLISL reduces the maximum link utilization by up to 72.6%. © 2022 IEEE.

关键词： Mixed reality

来源：评论

学校读者我要写书评

暂无评论

Harnessing Hierarchical label Distribution Variations in Test Agnostic Long-tail Recognition 41

Harnessing Hierarchical Label Distribution Variations in Tes...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Yang, Zhiyong Xu, Qianqian Wang, Zitai Li, Sicong Han, Boyu Bao, Shilong Cao, Xiaochun Huang, Qingming School of Computer Science and Tech. University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Tech. CAS China Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University China BDKM University of Chinese Academy of Sciences China

This paper explores test-agnostic long-tail recognition, a challenging long-tail task where the test label distributions are unknown and arbitrarily imbalanced. We argue that the variation in these distributions can be broken down hierarchically into global and local levels. The global ones reflect a broad range of diversity, while the local ones typically arise from milder changes, often focused on a particular neighbor. Traditional methods predominantly use a Mixture-of-Expert (MoE) approach, targeting a few fixed test label distributions that exhibit substantial global variations. However, the local variations are left unconsidered. To address this issue, we propose a new MoE strategy, DirMixE, which assigns experts to different Dirichlet meta-distributions of the label distribution, each targeting a specific aspect of local variations. Additionally, the diversity among these Dirichlet meta-distributions inherently captures global variations. This dual-level approach also leads to a more stable objective function, allowing us to sample different test distributions better to quantify the mean and variance of performance outcomes. Theoretically, we show that our proposed objective benefits from enhanced generalization by virtue of the variance-based regularization. Comprehensive experiments across multiple benchmarks confirm the effectiveness of DirMixE. The code is available at https://***/scongl/DirMixE. Copyright 2024 by the author(s)

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Integrating Multi-scale Contextualized information for Byte-based Neural Machine Translation

arXiv

引用

arXiv 2024年

作者： Huang, Langlin Feng, Yang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China Key Laboratory of AI Safety Chinese Academy of Sciences China University of Chinese Academy of Sciences China

Subword tokenization is a common method for vocabulary building in Neural Machine Translation (NMT) models. However, increasingly complex tasks have revealed its disadvantages. First, a vocabulary cannot be modified once it is learned, making it hard to adapt to new words. Second, in multilingual translation, the imbalance in data volumes across different languages spreads to the vocabulary, exacerbating translations involving low-resource languages. While byte-based tokenization addresses these issues, byte-based models struggle with the low information density inherent in UTF-8 byte sequences. Previous works enhance token semantics through local contextualization but fail to select an appropriate contextualizing scope based on the input. Consequently, we propose the Multi-Scale Contextualization (MSC) method, which learns contextualized information of varying scales across different hidden state dimensions. It then leverages the attention module to dynamically integrate the multi-scale contextualized information. Experiments show that MSC significantly outperforms subword-based and other byte-based methods in both multilingual and out-of-domain scenarios. We have uploaded the code to github1 © 2024, CC BY-NC-ND.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

LED: A Large-scale Real-world Paired Dataset for Event Camera Denoising

arXiv

引用

arXiv 2024年

作者： Duan, Yuxing Peng, Shihan Zhu, Lin Zhang, Wei Chang, Yi Zhong, Sheng Yan, Luxin National Key Lab of Multispectral Information Intelligent Processing Technology China Huazhong University of Science and Technology China Beijing Institute of Technology China Peng Cheng Laboratory China

Event camera has significant advantages in capturing dynamic scene information while being prone to noise interference, particularly in challenging conditions like low threshold and low illumination. However, most existing research focuses on gentle situations, hindering event camera applications in realistic complex scenarios. To tackle this limitation and advance the field, we construct a new paired real-world event denoising dataset (LED), including 3K sequences with 18K seconds of high-resolution (1200*680) event streams and showing three notable distinctions compared to others: diverse noise levels and scenes, larger-scale with high-resolution, and high-quality GT. Specifically, it contains stepped parameters and varying illumination with diverse scenarios. Moreover, based on the property of noise events inconsistency and signal events consistency, we propose a novel effective denoising framework(DED) using homogeneous dual events to generate the GT with better separating noise from the raw. Furthermore, we design a bio-inspired baseline leveraging Leaky-Integrate-and-Fire (LIF) neurons with dynamic thresholds to realize accurate denoising. The experimental results demonstrate that the remarkable performance of the proposed approach on different *** dataset and code are at https://***/Yee-Sing/led. © 2024, CC BY.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Cross-Validation Conformal Risk Control

Cross-Validation Conformal Risk Control

引用

IEEE International Symposium on information Theory

作者： Kfir M. Cohen Sangwoo Park Osvaldo Simeone Shlomo Shamai Shitz Department of Engineering King's Communications Learning and Information Processing (KCLIP) lab Centre for Intelligent Information Processing Systems (CIIPS) King's College London Viterbi Faculty of Electrical and Computing Engineering Technion-Israel Institute of Technology

ISBN: (数字)9798350382846

ISBN: (纸本)9798350382853

Conformal risk control (CRC) is a recently proposed technique that applies post-hoc to a conventional point predictor to provide calibration guarantees. Generalizing conformal prediction (CP), with CRC, calibration is ensured for a set predictor that is extracted from the point predictor to control a risk function such as the probability of miscoverage or the false negative rate. The original CRC requires the available data set to be split between training and validation data sets. This can be problematic when data availability is limited, resulting in inefficient set predictors. In this paper, a novel CRC method is introduced that is based on cross-validation, rather than on validation as the original CRC. The proposed cross-validation CRC (CV-CRC) extends a version of the jackknife-minmax from CP to CRC, allowing for the control of a broader range of risk functions. CV-CRC is proved to offer theoretical guarantees on the average risk of the set predictor. Furthermore, numerical experiments show that CV-CRC can reduce the average set size with respect to CRC when the available data are limited.

关键词： Training Metalearning Calibration information theory

来源：评论

学校读者我要写书评

暂无评论

Understanding the Robustness of 3D Object Detection with Bird'View Representations in Autonomous Driving

Understanding the Robustness of 3D Object Detection with Bir...

引用

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023

作者： Zhu, Zijian Zhang, Yichi Chen, Hai Dong, Yinpeng Zhao, Shu Ding, Wenbo Zhong, Jiachen Zheng, Shibao Institute of Image Communication and Network Engineering Shanghai Jiao Tong University China Institute for Ai Tsinghua University BNRist Center Thbi Lab Dept. of Comp. Sci. and Tech. China School of Computer Science and Technology Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Information Materials and Intelligent Sensing Laboratory of Anhui Province China Saic Motor Ai Lab Zhongguancun Laboratory China

ISBN: (纸本)9798350301298

3D object detection is an essential perception task in autonomous driving to understand the environments. The Bird's-Eye-View (BEV) representations have significantly improved the performance of 3D detectors with camera inputs on popular benchmarks. However, there still lacks a systematic understanding of the robustness of these vision-dependent BEV models, which is closely related to the safety of autonomous driving systems. In this paper, we evaluate the natural and adversarial robustness of various representative models under extensive settings, to fully understand their behaviors influenced by explicit BEV features compared with those without BEV. In addition to the classic settings, we propose a 3D consistent patch attack by applying adversarial patches in the 3D space to guarantee the spatiotemporal consistency, which is more realistic for the scenario of autonomous driving. With substantial experiments, we draw several findings: 1) BEV models tend to be more stable than previous methods under different natural conditions and common corruptions due to the expressive spatial representations;2) BEV models are more vulnerable to adversarial noises, mainly caused by the redundant BEV features;3) Camera-LiDARfusion models have superior performance under different settings with multi-modal inputs, but BEV fusion model is still vulnerable to adversarial noises of both point cloud and image. These findings alert the safety issue in the applications of BEV detectors and could facilitate the development of more robust models. © 2023 IEEE.

关键词： Autonomous driving

来源：评论

学校读者我要写书评

暂无评论

Text-Driven Generative Domain Adaptation with Spectral Consistency Regularization

Text-Driven Generative Domain Adaptation with Spectral Consi...

引用

International Conference on Computer Vision (ICCV)

作者： Zhenhuan Liu Liang Li Jiayu Xiao Zheng-Jun Zha Qingming Huang Institute of Computing Technology Key Laboratory of Intelligent Information Processing CAS University of Chinese Academy of Sciences University of Science and Technology of China Peng Cheng Laboratory

Combined with the generative prior of pre-trained models and the flexibility of text, text-driven generative domain adaptation can generate images from a wide range of target domains. However, current methods still suffer from overfitting and the mode collapse problem. In this paper, we analyze the mode collapse from the geometric point of view and reveal its relationship to the Hessian matrix of generator. To alleviate it, we propose the spectral consistency regularization to preserve the diversity of source domain without restricting the semantic adaptation to target domain. We also design granularity adaptive regularization to flexibly control the balance between diversity and stylization for target model. We conduct experiments for broad target domains compared with state-of-the-art methods and extensive ablation studies. The experiments demonstrate the effectiveness of our method to preserve the diversity of source domain and generate high fidelity target images. Source code has been released in https://***/Victarry/Adaptation-SCR.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FUZZY ALIGNMENTS IN DIRECTED ACYCLIC GRAPH FOR NON-AUTOREGRESSIVE MACHINE TRANSLATION

arXiv

引用

arXiv 2023年

作者： Ma, Zhengrui Shao, Chenze Gui, Shangtong Zhang, Min Feng, Yang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China Harbin Institute of Technology Shenzhen China

Non-autoregressive translation (NAT) reduces the decoding latency but suffers from performance degradation due to the multi-modality problem. Recently, the structure of directed acyclic graph has achieved great success in NAT, which tackles the multi-modality problem by introducing dependency between vertices. However, training it with negative log-likelihood loss implicitly requires a strict alignment between reference tokens and vertices, weakening its ability to handle multiple translation modalities. In this paper, we hold the view that all paths in the graph are fuzzily aligned with the reference sentence. We do not require the exact alignment but train the model to maximize a fuzzy alignment score between the graph and reference, which takes captured translations in all modalities into account. Extensive experiments on major WMT benchmarks show that our method substantially improves translation performance and increases prediction confidence, setting a new state of the art for NAT on the raw training data.1 Copyright © 2023, The Authors. All rights reserved.

关键词： Benchmarking

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：