arXiv subjects

Tao Xu

Publications and source records attributed to Tao Xu.

At least 91 records · Page 5Linked to original sources

arXiv2023

AI-Oriented Two-Phase Multi-Factor Authentication in SAGINs: Prospects and Challenges

Space-air-ground integrated networks (SAGINs), which have emerged as an expansion of terrestrial networks, provide flexible access, ubiquitous coverage, high-capacity backhaul, and emergency/disaster recovery for mobile users (MUs). While the massive benefits brought by SAGIN may improve the quality of service, unauthorized access to SAGIN entities is potentially dangerous. At present, conventional crypto-based authentication is facing challenges, such as the inability to provide continuous and transparent protection for MUs. In this article, we propose an AI-oriented two-phase multi-factor authentication scheme (ATMAS) by introducing intelligence to authentication. The satellite and network control center collaborate on continuous authentication, while unique spatial-temporal features, including service features and geographic features, are utilized to enhance the system security. Our further security analysis and performance evaluations show that ATMAS has proper security characteristics which can meet various security requirements. Moreover, we shed light on lightweight and efficient authentication mechanism design through a proper combination of spatial-temporal factors.

cs.NI↗

arXiv2023

Baryogenesis, Primordial Black Holes and MHz-GHz Gravitational Waves

Gravitational waves (GWs) in the MHz - GHz frequency range are motivated by a host of early Universe phenomena such as oscillons, preheating, and cosmic strings. We point out that baryogenesis too serves as a motivation to probe GWs in this frequency range. The connection is through primordial black holes (PBHs): on the one hand, PBHs induce baryogenesis by Hawking evaporating into a species that has baryon number and $CP$ violating decays; on the other, PBHs induce GWs through second order effects when the scalar fluctuations responsible for their formation re-enter the horizon. We describe the interplay of the parameters responsible for successful baryogenesis on the plane of the strain and frequency of the induced GWs, being careful to delineate regimes where PBH domination or washout effects occur. We provide semi-analytic scalings of the GW strain with the baryon number to entropy ratio and other parameters important for baryogenesis. Along the way, we sketch a solution to the dark matter-baryogenesis coincidence problem with two populations of PBHs, which leads to a double-peaked GW signal. Our results underscore the importance of probing the ultra high frequency GW frontier.

hep-ph↗

arXiv2023

Challenges and Opportunities of Content Optimization for Freeform User Interfaces

While recent innovations on shape technologies allow for the creation of displays with almost unlimited form factors, current graphical user interfaces still rely on rectangular layouts and contents. This rectangular legacy hinders the progress of freeform displays, which are particularly relevant for pervasive scenarios to display interactive dynamic content where and when needed. By challenging the prevailing layout tradition on rectangular displays, freeform user interfaces raise design challenges which call for exploring the interlink between computational approaches and user interface generation and adaptation. In this position paper we report on previous work on content optimization for freeform user interfaces and anticipate the upcoming challenges and opportunities.

cs.HC↗

arXiv2023

Correlating Gravitational Wave and Gamma-ray Signals from Primordial Black Holes

Asteroid-mass primordial black holes (PBH) can explain the observed dark matter abundance while being consistent with the current indirect detection constraints. These PBH can produce gamma-ray signals from Hawking radiation that are within the sensitivity of future measurements by the AMEGO and e-ASTROGAM experiments. PBH which give rise to such observable gamma-ray signals have a cosmic origin from large primordial curvature fluctuations. There must then be a companion, stochastic gravitational wave (GW) background produced by the same curvature fluctuations. We demonstrate that the resulting GW signals will be well within the sensitivity of future detectors such as LISA, DECIGO, BBO, and the Einstein Telescope. The multi-messenger signal from the observed gamma-rays and GW will allow a precise measurement of the primordial curvature perturbation that produces the PBH. Indeed, we argue that the resulting correlation between the two types of observations can provide a smoking-gun signal of PBH.

astro-ph.CO↗

arXiv2022

Robust Speech Recognition via Large-Scale Weak Supervision

We study the capabilities of speech processing systems trained simply to predict large amounts of transcripts of audio on the internet. When scaled to 680,000 hours of multilingual and multitask supervision, the resulting models generalize well to standard benchmarks and are often competitive with prior fully supervised results but in a zero-shot transfer setting without the need for any fine-tuning. When compared to humans, the models approach their accuracy and robustness. We are releasing models and inference code to serve as a foundation for further work on robust speech processing.

eess.AS↗

arXiv2022

Intelligent Computing: The Latest Advances, Challenges and Future

Computing is a critical driving force in the development of human civilization. In recent years, we have witnessed the emergence of intelligent computing, a new computing paradigm that is reshaping traditional computing and promoting digital revolution in the era of big data, artificial intelligence and internet-of-things with new computing theories, architectures, methods, systems, and applications. Intelligent computing has greatly broadened the scope of computing, extending it from traditional computing on data to increasingly diverse computing paradigms such as perceptual intelligence, cognitive intelligence, autonomous intelligence, and human-computer fusion intelligence. Intelligence and computing have undergone paths of different evolution and development for a long time but have become increasingly intertwined in recent years: intelligent computing is not only intelligence-oriented but also intelligence-driven. Such cross-fertilization has prompted the emergence and rapid advancement of intelligent computing. Intelligent computing is still in its infancy and an abundance of innovations in the theories, systems, and applications of intelligent computing are expected to occur soon. We present the first comprehensive survey of literature on intelligent computing, covering its theory fundamentals, the technological fusion of intelligence and computing, important applications, challenges, and future perspectives. We believe that this survey is highly timely and will provide a comprehensive reference and cast valuable insights into intelligent computing for academic and industrial researchers and practitioners.

cs.AI↗

arXiv2022

3D-Aware Encoding for Style-based Neural Radiance Fields

We tackle the task of NeRF inversion for style-based neural radiance fields, (e.g., StyleNeRF). In the task, we aim to learn an inversion function to project an input image to the latent space of a NeRF generator and then synthesize novel views of the original image based on the latent code. Compared with GAN inversion for 2D generative models, NeRF inversion not only needs to 1) preserve the identity of the input image, but also 2) ensure 3D consistency in generated novel views. This requires the latent code obtained from the single-view image to be invariant across multiple views. To address this new challenge, we propose a two-stage encoder for style-based NeRF inversion. In the first stage, we introduce a base encoder that converts the input image to a latent code. To ensure the latent code is view-invariant and is able to synthesize 3D consistent novel view images, we utilize identity contrastive learning to train the base encoder. Second, to better preserve the identity of the input image, we introduce a refining encoder to refine the latent code and add finer details to the output image. Importantly note that the novelty of this model lies in the design of its first-stage encoder which produces the closest latent code lying on the latent manifold and thus the refinement in the second stage would be close to the NeRF manifold. Through extensive experiments, we demonstrate that our proposed two-stage encoder qualitatively and quantitatively exhibits superiority over the existing encoders for inversion in both image reconstruction and novel-view rendering.

cs.CV↗

arXiv2022

Exploiting Dynamic and Fine-grained Semantic Scope for Extreme Multi-label Text Classification

Extreme multi-label text classification (XMTC) refers to the problem of tagging a given text with the most relevant subset of labels from a large label set. A majority of labels only have a few training instances due to large label dimensionality in XMTC. To solve this data sparsity issue, most existing XMTC methods take advantage of fixed label clusters obtained in early stage to balance performance on tail labels and head labels. However, such label clusters provide static and coarse-grained semantic scope for every text, which ignores distinct characteristics of different texts and has difficulties modelling accurate semantics scope for texts with tail labels. In this paper, we propose a novel framework TReaderXML for XMTC, which adopts dynamic and fine-grained semantic scope from teacher knowledge for individual text to optimize text conditional prior category semantic ranges. TReaderXML dynamically obtains teacher knowledge for each text by similar texts and hierarchical label information in training sets to release the ability of distinctly fine-grained label-oriented semantic scope. Then, TReaderXML benefits from a novel dual cooperative network that firstly learns features of a text and its corresponding label-oriented semantic scope by parallel Encoding Module and Reading Module, secondly embeds two parts by Interaction Module to regularize the text's representation by dynamic and fine-grained label-oriented semantic scope, and finally find target labels by Prediction Module. Experimental results on three XMTC benchmark datasets show that our method achieves new state-of-the-art results and especially performs well for severely imbalanced and sparse datasets.

cs.AI↗

arXiv2022

RAR-PINN algorithm for the data-driven vector-soliton solutions and parameter discovery of coupled nonlinear equations

This work aims to provide an effective deep learning framework to predict the vector-soliton solutions of the coupled nonlinear equations and their interactions. The method we propose here is a physics-informed neural network (PINN) combining with the residual-based adaptive refinement (RAR-PINN) algorithm. Different from the traditional PINN algorithm which takes points randomly, the RAR-PINN algorithm uses an adaptive point-fetching approach to improve the training efficiency for the solutions with steep gradients. A series of experiment comparisons between the RAR-PINN and traditional PINN algorithms are implemented to a coupled generalized nonlinear Schrödinger (CGNLS) equation as an example. The results indicate that the RAR-PINN algorithm has faster convergence rate and better approximation ability, especially in modeling the shape-changing vector-soliton interactions in the coupled systems. Finally, the RAR-PINN method is applied to perform the data-driven discovery of the CGNLS equation, which shows the dispersion and nonlinear coefficients can be well approximated.

math.NA↗

arXiv2022

Rural Pension System and Farmers' Participation in Residents' Social Insurance

As the ageing population and childlessness are increasing in rural China, social pensions will become the mainstream choice for farmers, and the level of social pensions must be supported by better social insurance. The paper compares the history of rural pension insurance system, outlines the current situation and problems, analyses China Family Panel Studies data and explores the key factors influencing farmers' participation through an empirical approach. The paper shows that residents' social pension insurance is facing problems in the rural areas such as low level of protection and weak management capacity, which have contributed to the under-insured rate, and finds that there is a significant impact on farmers' participation in insurance from personal characteristics factors such as gender, age, health and (family) financial factors such as savings, personal income, intergenerational mobility of funds. And use of the Internet can help farmers enroll in pension insurance. The paper argues for the need to continue to implement the rural revitalisation strategy, with the government as the lead and the market as the support, in a concerted effort to improve the protection and popularity of rural pension insurance.

econ.GN↗

arXiv2022

Efficient conditioned face animation using frontally-viewed embedding

As the quality of few shot facial animation from landmarks increases, new applications become possible, such as ultra low bandwidth video chat compression with a high degree of realism. However, there are some important challenges to tackle in order to improve the experience in real world conditions. In particular, the current approaches fail to represent profile views without distortions, while running in a low compute regime. We focus on this key problem by introducing a multi-frames embedding dubbed Frontalizer to improve profile views rendering. In addition to this core improvement, we explore the learning of a latent code conditioning generations along with landmarks to better convey facial expressions. Our dense models achieves 22% of improvement in perceptual quality and 73% reduction of landmark error over the first order model baseline on a subset of DFDC videos containing head movements. Declined with mobile architectures, our models outperform the previous state-of-the-art (improving perceptual quality by more than 16% and reducing landmark error by more than 47% on two datasets) while running on real time on iPhone 8 with very low bandwidth requirements.

cs.CV↗

arXiv2022

DAGAM: A Domain Adversarial Graph Attention Model for Subject Independent EEG-Based Emotion Recognition

One of the most significant challenges of EEG-based emotion recognition is the cross-subject EEG variations, leading to poor performance and generalizability. This paper proposes a novel EEG-based emotion recognition model called the domain adversarial graph attention model (DAGAM). The basic idea is to generate a graph to model multichannel EEG signals using biological topology. Graph theory can topologically describe and analyze relationships and mutual dependency between channels of EEG. Then, unlike other graph convolutional networks, self-attention pooling is applied to benefit salient EEG feature extraction from the graph, which effectively improves the performance. Finally, after graph pooling, the domain adversarial based on the graph is employed to identify and handle EEG variation across subjects, efficiently reaching good generalizability. We conduct extensive evaluations on two benchmark datasets (SEED and SEED IV) and obtain state-of-the-art results in subject-independent emotion recognition. Our model boosts the SEED accuracy to 92.59% (4.69% improvement) with the lowest standard deviation of 3.21% (2.92% decrements) and SEED IV accuracy to 80.74% (6.90% improvement) with the lowest standard deviation of 4.14% (3.88% decrements) respectively.

eess.SP↗

arXiv2022

Optimal configuration of cooperative stationary and mobile energy storage considering ambient temperature: A case for Winter Olympic Game

The international mega-event, such as the Winter Olympic Game, has been considered as one of the most carbon intensive activities worldwide. The commitment of fully renewable energy accommodation and utilization while ensuring the extreme high reliability has brought significant challenges on system operation due to the stochastic nature of the renewables. The battery energy storage system (BESS) composed of stationary energy storage system (SESS) and shared mobile energy storage system (MESS) can be utilized to meet the requirements of short-term load surges, renewable accommodation and emergency power supply for important loads during the mega-event. The BESS can continue to serve the venues electricity consumption to satisfy the carbon neutrality after the event. On the other hand, the low ambient temperature of Winter Olympic game has significant impact on BESSs degradation and performance which need to be integrated to the charging and discharging model of BESS. To this end, a joint two-stage optimal configuration method considering the ambient temperature of SESS and MESS has been developed to support the mega-event carbon neutrality, to reduce redundant BESS capacity allocation and improve the system life cycle cost-benefit. Simulation results have demonstrated the rationality and effectiveness of the collaborative operation of SESS and the MESS under various scenarios.

eess.SY↗

arXiv2022

Multi-objective Distributed Optimization for Zonal Distribution System with Multi-Microgrids

The issue of voltage variations caused by integration of renewables has been addressed in this paper through distributed management of Microgrids (MGs). The distribution network (DN) takes the network losses and voltage quality as objectives, an alternating direction method of multipliers (ADMM) with adaptive penalty modulation has been proposed to realize distributed optimization with improved convergence. On the basis of satisfying the optimization target on the system level, the individual MG manages the controllable resources inside the MG to minimize the operating cost on the lower level. The feasibility and effectiveness of the proposed method has been demonstrated on a modified IEEE 33-bus system.

eess.SY↗

arXiv2022

Text and Code Embeddings by Contrastive Pre-Training

Text embeddings are useful features in many applications such as semantic search and computing text similarity. Previous work typically trains models customized for different use cases, varying in dataset choice, training objective and model architecture. In this work, we show that contrastive pre-training on unsupervised data at scale leads to high quality vector representations of text and code. The same unsupervised text embeddings that achieve new state-of-the-art results in linear-probe classification also display impressive semantic search capabilities and sometimes even perform competitively with fine-tuned models. On linear-probe classification accuracy averaging over 7 tasks, our best unsupervised model achieves a relative improvement of 4% and 1.8% over previous best unsupervised and supervised text embedding models respectively. The same text embeddings when evaluated on large-scale semantic search attains a relative improvement of 23.4%, 14.7%, and 10.6% over previous best unsupervised methods on MSMARCO, Natural Questions and TriviaQA benchmarks, respectively. Similarly to text embeddings, we train code embedding models on (text, code) pairs, obtaining a 20.8% relative improvement over prior best work on code search.

cs.CL↗

arXiv2021

Alleviating Noisy-label Effects in Image Classification via Probability Transition Matrix

Deep-learning-based image classification frameworks often suffer from the noisy label problem caused by the inter-observer variation. Recent studies employed learning-to-learn paradigms (e.g., Co-teaching and JoCoR) to filter the samples with noisy labels from the training set. However, most of them use a simple cross-entropy loss as the criterion for noisy label identification. The hard samples, which are beneficial for classifier learning, are often mistakenly treated as noises in such a setting since both the hard samples and ones with noisy labels lead to a relatively larger loss value than the easy cases. In this paper, we propose a plugin module, namely noise ignoring block (NIB), consisting of a probability transition matrix and an inter-class correlation (IC) loss, to separate the hard samples from the mislabeled ones, and further boost the accuracy of image classification network trained with noisy labels. Concretely, our IC loss is calculated as Kullback-Leibler divergence between the network prediction and the accumulative soft label generated by the probability transition matrix. Such that, with the lower value of IC loss, the hard cases can be easily distinguished from mislabeled cases. Extensive experiments are conducted on natural and medical image datasets (CIFAR-10 and ISIC 2019). The experimental results show that our NIB module consistently improves the performances of the state-of-the-art robust training methods.

cs.CV↗

arXiv2021

Unsupervised Neural Machine Translation with Generative Language Models Only

We show how to derive state-of-the-art unsupervised neural machine translation systems from generatively pre-trained language models. Our method consists of three steps: few-shot amplification, distillation, and backtranslation. We first use the zero-shot translation ability of large pre-trained language models to generate translations for a small set of unlabeled sentences. We then amplify these zero-shot translations by using them as few-shot demonstrations for sampling a larger synthetic dataset. This dataset is distilled by discarding the few-shot demonstrations and then fine-tuning. During backtranslation, we repeatedly generate translations for a set of inputs and then fine-tune a single language model on both directions of the translation task at once, ensuring cycle-consistency by swapping the roles of gold monotext and generated translations when fine-tuning. By using our method to leverage GPT-3's zero-shot translation capability, we achieve a new state-of-the-art in unsupervised translation on the WMT14 English-French benchmark, attaining a BLEU score of 42.1.

cs.CL↗

arXiv2021

Deep Image Synthesis from Intuitive User Input: A Review and Perspectives

In many applications of computer graphics, art and design, it is desirable for a user to provide intuitive non-image input, such as text, sketch, stroke, graph or layout, and have a computer system automatically generate photo-realistic images that adhere to the input content. While classic works that allow such automatic image content generation have followed a framework of image retrieval and composition, recent advances in deep generative models such as generative adversarial networks (GANs), variational autoencoders (VAEs), and flow-based methods have enabled more powerful and versatile image generation tasks. This paper reviews recent works for image synthesis given intuitive user input, covering advances in input versatility, image generation methodology, benchmark datasets, and evaluation metrics. This motivates new perspectives on input representation and interactivity, cross pollination between major image generation paradigms, and evaluation and comparison of generation methods.

cs.CV↗