检索结果-内蒙古大学图书馆

Revealing Performance Issues in Server-Side WebAssembly Runtimes via Differential Testing 23

学校读者我要写书评

暂无评论

Revealing Performance Issues in Server-Side WebAssembly Runt...

Proceedings of the 38th IEEE/ACM International Conference on Automated Software Engineering

作者： Shuyao Jiang Ruiying Zeng Zihao Rao Jiazhen Gu Yangfan Zhou Michael R. Lyu Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong China School of Computer Science Fudan University Shanghai China and Shanghai Key Laboratory of Intelligent Information Processing Shanghai Chian

ISBN: (纸本)9798350329964

WebAssembly (Wasm) is a bytecode format originally serving as a compilation target for Web applications. It has recently been used increasingly on the server side, e.g., providing a safer, faster, and more portable alternative to Linux containers. With the popularity of server-side Wasm applications, it is essential to study performance issues (i.e., abnormal latency) in Wasm runtimes, as they may cause a significant impact on server-side applications. However, there is still a lack of attention to performance issues in server-side Wasm runtimes. In this paper, we design a novel differential testing approach WarpDiff to identify performance issues in server-side Wasm runtimes. The key insight is that in normal cases, the execution time of the same test case on different Wasm runtimes should follow an oracle ratio. We identify abnormal cases where the execution time ratio significantly deviates from the oracle ratio and subsequently locate the Wasm runtimes that cause the performance issues. We apply WarpDiff to test five popular server-side Wasm runtimes using 123 test cases from the LLVM test suite and demonstrate the top 10 abnormal cases we identified. We further conduct an in-depth analysis of these abnormal cases and summarize seven performance issues, all of which have been confirmed by the developers. We hope our work can inspire future investigation on improving Wasm runtime implementation and thus promoting the development of server-side Wasm applications.

关键词： WebAssembly

Pre-trained models for natural language processing: A survey

学校读者我要写书评

暂无评论

science China(Technological sciences) 2020年第10期63卷 1872-1897页

作者： QIU XiPeng SUN TianXiang XU YiGe SHAO YunFan DAI Ning HUANG XuanJing School of Computer Science Fudan UniversityShanghai 200433China Shanghai Key Laboratory of Intelligent Information Processing Shanghai 200433China

Recently, the emergence of pre-trained models(PTMs) has brought natural language processing(NLP) to a new era. In this survey, we provide a comprehensive review of PTMs for NLP. We first briefly introduce language representation learning and its research progress. Then we systematically categorize existing PTMs based on a taxonomy from four different perspectives. Next,we describe how to adapt the knowledge of PTMs to downstream tasks. Finally, we outline some potential directions of PTMs for future research. This survey is purposed to be a hands-on guide for understanding, using, and developing PTMs for various NLP tasks.

关键词： deep learning neural network natural language processing pre-trained model distributed representation word embedding self-supervised learning language modelling

Ordinal distribution regression for gait-based age estimation

学校读者我要写书评

暂无评论

science China(information sciences) 2020年第2期63卷 21-34页

作者： Haiping ZHU Yuheng ZHANG Guohao LI Junping ZHANG Hongming SHAN Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Department of Biomedical Engineering Rensselaer Polytechnic Institute

computer vision researchers prefer to estimate age from face images because facial features provide useful information. However, estimating age from face images becomes challenging when people are distant from the camera or occluded. A person’s gait is a unique biometric feature that can be perceived efficiently even at a distance. Thus, gait can be used to predict age when face images are not ***, existing gait-based classification or regression methods ignore the ordinal relationship of different ages, which is an important clue for age estimation. This paper proposes an ordinal distribution regression with a global and local convolutional neural network for gait-based age estimation. Specifically, we decompose gait-based age regression into a series of binary classifications to incorporate the ordinal age ***, an ordinal distribution loss is proposed to consider the inner relationships among these classifications by penalizing the distribution discrepancy between the estimated value and the ground truth. In addition,our neural network comprises a global and three local sub-networks, and thus, is capable of learning the global structure and local details from the head, body, and feet. Experimental results indicate that the proposed approach outperforms state-of-the-art gait-based age estimation methods on the OULP-Age dataset.

关键词： computer vision deep learning ordinal distribution regression global and local features gaitbased age estimation

Learning Survival Distribution with Implicit Survival Function

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Ling, Yu Tan, Weimin Yan, Bo School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Shanghai Collaborative Innovation Center of Intelligent Visual Computing Fudan University Shanghai China

Survival analysis aims at modeling the relationship between covariates and event occurrence with some untracked (censored) samples. In implementation, existing methods model the survival distribution with strong assumptions or in a discrete time space for likelihood estimation with censorship, which leads to weak generalization. In this paper, we propose Implicit Survival Function (ISF) based on Implicit Neural Representation for survival distribution estimation without strong assumptions, and employ numerical integration to approximate the cumulative distribution function for prediction and optimization. Experimental results show that ISF outperforms the state-of-the-art methods in three public datasets and has robustness to the hyperparameter controlling estimation precision. Copyright © 2023, The Authors. All rights reserved.

关键词： Distribution functions

Inference-Time Decontamination: Reusing Leaked Benchmarks for Large Language Model Evaluation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhu, Qin Cheng, Qinyuan Peng, Runyu Li, Xiaonan Liu, Tengxiao Peng, Ru Qiu, Xipeng Huang, Xuanjing School of Computer Science Fudan University China Shanghai Key Laboratory of Intelligent Information Processing Fudan University China College of Computer Science and Technology Zhejiang University China

The training process of large language models (LLMs) often involves varying degrees of test data contamination (Yang et al., 2023b). Although current LLMs are achieving increasingly better performance on various benchmarks, their performance in practical applications does not always match their benchmark results. Leakage of benchmarks can prevent the accurate assessment of LLMs’ true performance. However, constructing new benchmarks is costly, labor-intensive and still carries the risk of leakage. Therefore, in this paper, we ask the question "Can we reuse these leaked benchmarks for LLM evaluation?" We propose Inference-Time Decontamination (ITD) to address this issue by detecting and rewriting leaked samples without altering their difficulties. ITD can mitigate performance inflation caused by memorizing leaked benchmarks. Our proof-of-concept experiments demonstrate that ITD reduces inflated accuracy by 22.9% on GSM8K and 19.0% on MMLU. On MMLU, using Inference-time Decontamination can lead to a decrease in the results of Phi3 and Mistral by 6.7% and 3.6% respectively. We hope that ITD can provide more truthful evaluation results for large language models. Copyright © 2024, The Authors. All rights reserved.

关键词： Decontamination

Motion Matters: Difference-based Multi-scale Learning for Infrared UAV Detection

学校读者我要写书评

暂无评论

Motion Matters: Difference-based Multi-scale Learning for In...

IEEE computer Society Conference on computer Vision and Pattern Recognition Workshops (CVPRW)

作者： Ruian He Shili Zhou Ri Cheng Yuqi Sun Weimin Tan Bo Yan School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Shanghai Collaborative Innovation Center of Intelligent Visual Computing Fudan University Shanghai China

Unmanned Aerial Vehicle (UAV) detection in the wild is a challenging task due to the presence of background noise and the varying size of the object. To address these obstacles, we propose a novel learning framework for robust UAV detectors, which we call Difference-based Multi-scale Learning (DML). We argue that motion information matters in UAV detection because of the low recognition in one frame. Our method utilizes the frame difference of multiple previous frames, extracting motion information and blocking background noise. We also fuse multiple spatial-temporal scales for training and inferencing, enabling fusion from different sources. In addition, to better evaluate the performance of UAV detection in different scales, we propose Multi-Scale Average Precision (MSAP) metric to aggregate the detection accuracy over multiple scales. Through extensive experiments, we demonstrate that our proposed approach improves the detection accuracy of baseline models. Notably, we achieve SOTA performance in the 3rd Anti-UAV Challenge, with 2nd place in Track 2 and 4th place in Track 1. 1

关键词：

M3-20M: A Large-Scale Multi-Modal Molecule Dataset for AI-driven Drug Design and Discovery

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Guo, Siyuan Wang, Lexuan Jin, Chang Wang, Jinxian Peng, Han Shi, Huayang Li, Wengen Guan, Jihong Zhou, Shuigeng Department of Computer Science and Technology Tongji University No. 4800 Cao’an Road Shanghai201804 China Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University 2005 Songhu Road Shanghai200438 China

This paper introduces M3-20M, a large-scale Multi-Modal Molecule dataset that contains over 20 million molecules, with the data mainly being integrated from existing databases and partially generated by large language models. Designed to support AI-driven drug design and discovery, M3-20M is 71 times more in the number of molecules than the largest existing dataset, providing an unprecedented scale that can highly benefit the training or fine-tuning of models, including large language models for drug design and discovery tasks. This dataset integrates one-dimensional SMILES, two-dimensional molecular graphs, three-dimensional molecular structures, physicochemical properties, and textual descriptions collected through web crawling and generated using GPT-3.5, offering a comprehensive view of each molecule. To demonstrate the power of M3-20M in drug design and discovery, we conduct extensive experiments on two key tasks: molecule generation and molecular property prediction, using large language models including GLM4, GPT-3.5, GPT-4, and Llama3-8b. Our experimental results show that M3-20M can significantly boost model performance in both tasks. Specifically, it enables the models to generate more diverse and valid molecular structures and achieve higher property prediction accuracy than existing single-modal datasets, which validates the value and potential of M3-20M in supporting AI-driven drug design and discovery. The dataset is available at https://***/bz99bz/M-3. Copyright © 2024, The Authors. All rights reserved.

关键词： Web crawler

Instruct-NeuralTalker: Editing Audio-Driven Talking Radiance Fields with Instructions

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Sun, Yuqi He, Ruian Tan, Weimin Yan, Bo School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Shanghai Collaborative Innovation Center of Intelligent Visual Computing Fudan University Shanghai China

Recent neural talking radiance field methods have shown great success in photorealistic audio-driven talking face synthesis. In this paper, we propose the first novel interactive framework that utilizes human instructions to edit talking radiance fields to achieve personalized talking face generation. Given a short speech video, we first build an efficient talking radiance field and then apply the latest conditional diffusion model to edit images with human instructions during the optimization. To ensure audio-lip synchronization during the editing process, we propose a progressive dataset updating strategy to ensure successful editing while preventing distortion of lip shapes. We also introduce a lightweight refinement network for complementing image details and achieving controllable detail generation in the final rendered image. Our method enables real-time rendering at up to 30FPS on consumer hardware. Multiple metrics and user verification show that our approach significantly improves rendering quality compared to state-of-the-art methods. © 2023, CC BY-NC-ND.

关键词： Rendering (computer graphics)

Uncer2Natural: Uncertainty-Aware Unsupervised Image Denoising

学校读者我要写书评

暂无评论

Uncer2Natural: Uncertainty-Aware Unsupervised Image Denoisin...

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

作者： Chenyu Huang Weimin Tan Jiaxing Shi Zhen Xing Bo Yan School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Shanghai Collaborative Innovation Center of Intelligent Visual Computing Fudan University Shanghai China

Recently, unsupervised image denoising methods learning from paired noisy samples have received increasing attention. These methods build on the idea that the mean of multiple noisy images of the same scene is the ideal clean image. However, these methods ignore the effect of Aleatoric uncertainty in the noisy image (e.g., pixels deviating from the expected distribution). The presence of Aleatoric uncertainty causes degradation of the reconstructed target pixels, resulting in high uncertainty for these pixels (i.e., low confidence), which in turn leads to sub-optimal denoising results. To address this problem, we propose a novel uncertainty-aware unsupervised image denoising method named Uncer2Natural (U2N). It dynamically predicts the Aleatoric uncertainty for each noisy sample and produces satisfactory denoising results by reducing the effect of Aleatoric uncertainty. Extensive experimental results show that U2N outperforms state-of-the- art unsupervised image denoising methods in terms of both quantitative metrics and qualitative visual quality.

关键词： Degradation Visualization Uncertainty Art Noise reduction Signal processing Noise measurement