arXiv subjects

Wei Xu

Publications and source records attributed to Wei Xu.

At least 325 records · Page 18Linked to original sources

arXiv2024

Analysis of Pseudo-Random Number Generators in QMC-SSE Method

In the quantum Monte Carlo (QMC) method, the Pseudo-Random Number Generator (PRNG) plays a crucial role in determining the computation time. However, the hidden structure of the PRNG may lead to serious issues such as the breakdown of the Markov process. Here, we systematically analyze the performance of the different PRNGs on the widely used QMC method -- stochastic series expansion (SSE) algorithm. To quantitatively compare them, we introduce a quantity called QMC efficiency that can effectively reflect the efficiency of the algorithms. After testing several representative observables of the Heisenberg model in one and two dimensions, we recommend using LCG as the best choice of PRNGs. Our work can not only help improve the performance of the SSE method but also shed light on the other Markov-chain-based numerical algorithms.

cond-mat.str-el↗

arXiv2024

RecAI: Leveraging Large Language Models for Next-Generation Recommender Systems

This paper introduces RecAI, a practical toolkit designed to augment or even revolutionize recommender systems with the advanced capabilities of Large Language Models (LLMs). RecAI provides a suite of tools, including Recommender AI Agent, Recommendation-oriented Language Models, Knowledge Plugin, RecExplainer, and Evaluator, to facilitate the integration of LLMs into recommender systems from multifaceted perspectives. The new generation of recommender systems, empowered by LLMs, are expected to be more versatile, explainable, conversational, and controllable, paving the way for more intelligent and user-centric recommendation experiences. We hope the open-source of RecAI can help accelerate evolution of new advanced recommender systems. The source code of RecAI is available at \url{https://github.com/microsoft/RecAI}.

cs.IR↗

arXiv2024

A "User Experience 3.0 (UX 3.0)" Paradigm Framework: User Experience Design for Human-Centered AI Systems

The human-centered artificial intelligence (HCAI) design approach, the user-centered design (UCD) version in the intelligence era, has been promoted to address potential negative issues caused by AI technology; user experience design (UXD) is specifically called out to facilitate the design and development of human-centered AI systems. Over the last three decades, user experience (UX) practice can be divided into three stages in terms of technology platform, user needs, design philosophy, ecosystem, scope, focus, and methodology of UX practice. UX practice is moving towards the intelligence era. Still, the existing UX paradigm mainly aims at non-intelligent systems and lacks a systematic approach to address UX for designing and developing human-centered AI products and systems. The intelligence era has put forward new demands on the UX paradigm. This paper proposes a "UX 3.0" paradigm framework and the corresponding UX methodology for UX practice in the intelligence era. The "UX 3.0" paradigm framework includes four categories of emerging experiences in the intelligence era: ecosystem-based experience, innovation-enabled experience, AI-enabled experience, and human-AI interaction-based experience, each compelling us to enhance current UX practice in terms of design philosophy, scope, focus, and methodology. We believe that the "UX 3.0" paradigm helps enhance existing UX practice and provides methodological support for the research and applications of UX in developing human-centered AI systems. Finally, this paper looks forward to future work implementing the "UX 3.0" paradigm.

cs.HC↗

arXiv2024

Seamless Virtual Reality with Integrated Synchronizer and Synthesizer for Autonomous Driving

Virtual reality (VR) is a promising data engine for autonomous driving (AD). However, data fidelity in this paradigm is often degraded by VR inconsistency, for which the existing VR approaches become ineffective, as they ignore the inter-dependency between low-level VR synchronizer designs (i.e., data collector) and high-level VR synthesizer designs (i.e., data processor). This paper presents a seamless virtual reality SVR platform for AD, which mitigates such inconsistency, enabling VR agents to interact with each other in a shared symbiotic world. The crux to SVR is an integrated synchronizer and synthesizer IS2 design, which consists of a drift-aware lidar-inertial synchronizer for VR colocation and a motion-aware deep visual synthesis network for augmented reality image generation. We implement SVR on car-like robots in two sandbox platforms, achieving a cm-level VR colocalization accuracy and 3.2% VR image deviation, thereby avoiding missed collisions or model clippings. Experiments show that the proposed SVR reduces the intervention times, missed turns, and failure rates compared to other benchmarks. The SVR-trained neural network can handle unseen situations in real-world environments, by leveraging its knowledge learnt from the VR space.

cs.RO↗

arXiv2024

ELA: Efficient Local Attention for Deep Convolutional Neural Networks

The attention mechanism has gained significant recognition in the field of computer vision due to its ability to effectively enhance the performance of deep neural networks. However, existing methods often struggle to effectively utilize spatial information or, if they do, they come at the cost of reducing channel dimensions or increasing the complexity of neural networks. In order to address these limitations, this paper introduces an Efficient Local Attention (ELA) method that achieves substantial performance improvements with a simple structure. By analyzing the limitations of the Coordinate Attention method, we identify the lack of generalization ability in Batch Normalization, the adverse effects of dimension reduction on channel attention, and the complexity of attention generation process. To overcome these challenges, we propose the incorporation of 1D convolution and Group Normalization feature enhancement techniques. This approach enables accurate localization of regions of interest by efficiently encoding two 1D positional feature maps without the need for dimension reduction, while allowing for a lightweight implementation. We carefully design three hyperparameters in ELA, resulting in four different versions: ELA-T, ELA-B, ELA-S, and ELA-L, to cater to the specific requirements of different visual tasks such as image classification, object detection and sementic segmentation. ELA can be seamlessly integrated into deep CNN networks such as ResNet, MobileNet, and DeepLab. Extensive evaluations on the ImageNet, MSCOCO, and Pascal VOC datasets demonstrate the superiority of the proposed ELA module over current state-of-the-art methods in all three aforementioned visual tasks.

cs.CV↗

arXiv2024

Probabilistic Semantic Communication over Wireless Networks with Rate Splitting

In this paper, the problem of joint transmission and computation resource allocation for probabilistic semantic communication (PSC) system with rate splitting multiple access (RSMA) is investigated. In the considered model, the base station (BS) needs to transmit a large amount of data to multiple users with RSMA. Due to limited communication resources, the BS is required to utilize semantic communication techniques to compress the large-sized data. The semantic communication is enabled by shared probability graphs between the BS and the users. The probability graph can be used to further compress the transmission data at the BS, while the received compressed semantic information can be recovered through using the same shared probability graph at each user side. The semantic information compression progress consumes additional computation power at the BS, which inevitably decreases the transmission power due to limited total power budget. Considering both the effect of semantic compression ratio and computation power, the semantic rate expression for RSMA is first obtained. Then, based on the obtained rate expression, an optimization problem is formulated with the aim of maximizing the sum of semantic rates of all users under total power, semantic compression ratio, and rate allocation constraints. To tackle this problem, an iterative algorithm is proposed, where the rate allocation and transmit beamforming design subproblem is solved using a successive convex approximation method, and the semantic compression ratio subproblem is addressed using a greedy algorithm. Numerical results validate the effectiveness of the proposed scheme.

cs.IT↗

arXiv2024

Deep-Unfolded Joint Activity and Data Detection for Grant-Free Transmission in Cell-Free Systems

Massive grant-free transmission and cell-free wireless communication systems have emerged as pivotal enablers for massive machine-type communication. This paper proposes a deep-unfolding-based joint activity and data detection (DU-JAD) algorithm for massive grant-free transmission in cell-free systems. We first formulate a joint activity and data detection optimization problem, which we solve approximately using forward-backward splitting (FBS). We then apply deep unfolding to FBS to optimize algorithm parameters using machine learning. In order to improve data detection (DD) performance, reduce algorithm complexity, and enhance active user detection (AUD), we employ a momentum strategy, an approximate posterior mean estimator, and a novel soft-output AUD module, respectively. Simulation results confirm the efficacy of DU-JAD for AUD and DD.

cs.IT↗

arXiv2024

Spin: An Efficient Secure Computation Framework with GPU Acceleration

Accuracy and efficiency remain challenges for multi-party computation (MPC) frameworks. Spin is a GPU-accelerated MPC framework that supports multiple computation parties and a dishonest majority adversarial setup. We propose optimized protocols for non-linear functions that are critical for machine learning, as well as several novel optimizations specific to attention that is the fundamental unit of Transformer models, allowing Spin to perform non-trivial CNNs training and Transformer inference without sacrificing security. At the backend level, Spin leverages GPU, CPU, and RDMA-enabled smart network cards for acceleration. Comprehensive evaluations demonstrate that Spin can be up to $2\times$ faster than the state-of-the-art for deep neural network training. For inference on a Transformer model with 18.9 million parameters, our attention-specific optimizations enable Spin to achieve better efficiency, less communication, and better accuracy.

cs.CR↗

arXiv2024

Digital versus Analog Transmissions for Federated Learning over Wireless Networks

In this paper, we quantitatively compare these two effective communication schemes, i.e., digital and analog ones, for wireless federated learning (FL) over resource-constrained networks, highlighting their essential differences as well as their respective application scenarios. We first examine both digital and analog transmission methods, together with a unified and fair comparison scheme under practical constraints. A universal convergence analysis under various imperfections is established for FL performance evaluation in wireless networks. These analytical results reveal that the fundamental difference between the two paradigms lies in whether communication and computation are jointly designed or not. The digital schemes decouple the communication design from specific FL tasks, making it difficult to support simultaneous uplink transmission of massive devices with limited bandwidth. In contrast, the analog communication allows over-the-air computation (AirComp), thus achieving efficient spectrum utilization. However, computation-oriented analog transmission reduces power efficiency, and its performance is sensitive to computational errors. Finally, numerical simulations are conducted to verify these theoretical observations.

cs.IT↗

arXiv2024

Stanceosaurus 2.0: Classifying Stance Towards Russian and Spanish Misinformation

The Stanceosaurus corpus (Zheng et al., 2022) was designed to provide high-quality, annotated, 5-way stance data extracted from Twitter, suitable for analyzing cross-cultural and cross-lingual misinformation. In the Stanceosaurus 2.0 iteration, we extend this framework to encompass Russian and Spanish. The former is of current significance due to prevalent misinformation amid escalating tensions with the West and the violent incursion into Ukraine. The latter, meanwhile, represents an enormous community that has been largely overlooked on major social media platforms. By incorporating an additional 3,874 Spanish and Russian tweets over 41 misinformation claims, our objective is to support research focused on these issues. To demonstrate the value of this data, we employed zero-shot cross-lingual transfer on multilingual BERT, yielding results on par with the initial Stanceosaurus study with a macro F1 score of 43 for both languages. This underlines the viability of stance classification as an effective tool for identifying multicultural misinformation.

cs.CL↗

arXiv2024

Constrained Decoding for Cross-lingual Label Projection

Zero-shot cross-lingual transfer utilizing multilingual LLMs has become a popular learning paradigm for low-resource languages with no labeled training data. However, for NLP tasks that involve fine-grained predictions on words and phrases, the performance of zero-shot cross-lingual transfer learning lags far behind supervised fine-tuning methods. Therefore, it is common to exploit translation and label projection to further improve the performance by (1) translating training data that is available in a high-resource language (e.g., English) together with the gold labels into low-resource languages, and/or (2) translating test data in low-resource languages to a high-source language to run inference on, then projecting the predicted span-level labels back onto the original test data. However, state-of-the-art marker-based label projection methods suffer from translation quality degradation due to the extra label markers injected in the input to the translation model. In this work, we explore a new direction that leverages constrained decoding for label projection to overcome the aforementioned issues. Our new method not only can preserve the quality of translated texts but also has the versatility of being applicable to both translating training and translating test data strategies. This versatility is crucial as our experiments reveal that translating test data can lead to a considerable boost in performance compared to translating only training data. We evaluate on two cross-lingual transfer tasks, namely Named Entity Recognition and Event Argument Extraction, spanning 20 languages. The results demonstrate that our approach outperforms the state-of-the-art marker-based method by a large margin and also shows better performance than other label projection methods that rely on external word alignment.

cs.CL↗

arXiv2024

Diffusion Approximations for Self-excited Systems with Applications to General Branching Processes

In this work, several convergence results are established for nearly critical self-excited systems in which event arrivals are described by multivariate marked Hawkes point processes. Under some mild high-frequency assumptions, the rescaled density process behaves asymptotically like a multi-type continuous-state branching process with immigration, which is the unique solution to a multi-dimensional stochastic differential equation with dynamical mechanism similar to that of multivariate Hawkes processes. To illustrate the strength of these limit results, we further establish diffusion approximations for multi-type Crump-Mode-Jagers branching processes counted with various characteristics by linking them to marked Hawkes shot noise processes. In particular, an interesting phenomenon in queueing theory, well-known as state space collapse, is observed in the behavior of the population structure at a large time scale. This phenomenon reveals that the rescaled complex biological system can be recovered from its population process by a lifting map.

math.PR↗

arXiv2024

Stochastic Volterra Equations for the Local Times of Spectrally Positive Stable Processes

This paper is concerned with the evolution dynamics of local times of a spectrally positive stable process in the spatial direction. The main results state that conditioned on the finiteness of the first time at which the local time at zero exceeds a given value, the local times at positive half line are equal in distribution to the unique solution of a stochastic Volterra equation driven by a Poisson random measure whose intensity coincides with the Lévy measure. This helps us to provide not only a simple proof for the Hölder regularity, but also a uniform upper bound for all moments of the Hölder coefficient as well as a maximal inequality for the local times. Moreover, based on this stochastic Volterra equation, we extend the method of duality to establish an exponential-affine representation of the Laplace functional in terms of the unique solution of a nonlinear Volterra integral equation associated with the Laplace exponent of the stable process.

math.PR↗

arXiv2024

Joint Semantic Communication and Target Sensing for 6G Communication System

This paper investigates the secure resource allocation for a downlink integrated sensing and communication system with multiple legal users and potential eavesdroppers. In the considered model, the base station (BS) simultaneously transmits sensing and communication signals through beamforming design, where the sensing signals can be viewed as artificial noise to enhance the security of communication signals. To further enhance the security in the semantic layer, the semantic information is extracted from the original information before transmission. The user side can only successfully recover the received information with the help of the knowledge base shared with the BS, which is stored in advance. Our aim is to maximize the sum semantic secrecy rate of all users while maintaining the minimum quality of service for each user and guaranteeing overall sensing performance. To solve this sum semantic secrecy rate maximization problem, an iterative algorithm is proposed using the alternating optimization method. The simulation results demonstrate the superiority of the proposed algorithm in terms of secure semantic communication and reliable detection.

cs.IT↗

arXiv2024

Continuous Field Reconstruction from Sparse Observations with Implicit Neural Networks

Reliably reconstructing physical fields from sparse sensor data is a challenge that frequently arises in many scientific domains. In practice, the process generating the data often is not understood to sufficient accuracy. Therefore, there is a growing interest in using the deep neural network route to address the problem. This work presents a novel approach that learns a continuous representation of the physical field using implicit neural representations (INRs). Specifically, after factorizing spatiotemporal variability into spatial and temporal components using the separation of variables technique, the method learns relevant basis functions from sparsely sampled irregular data points to develop a continuous representation of the data. In experimental evaluations, the proposed model outperforms recent INR methods, offering superior reconstruction quality on simulation data from a state-of-the-art climate model and a second dataset that comprises ultra-high resolution satellite-based sea surface temperature fields.

cs.LG↗

arXiv2024

VONet: Unsupervised Video Object Learning With Parallel U-Net Attention and Object-wise Sequential VAE

Unsupervised video object learning seeks to decompose video scenes into structural object representations without any supervision from depth, optical flow, or segmentation. We present VONet, an innovative approach that is inspired by MONet. While utilizing a U-Net architecture, VONet employs an efficient and effective parallel attention inference process, generating attention masks for all slots simultaneously. Additionally, to enhance the temporal consistency of each mask across consecutive video frames, VONet develops an object-wise sequential VAE framework. The integration of these innovative encoder-side techniques, in conjunction with an expressive transformer-based decoder, establishes VONet as the leading unsupervised method for object learning across five MOVI datasets, encompassing videos of diverse complexities. Code is available at https://github.com/hnyu/vonet.

cs.CV↗

arXiv2024

New research paradigms and agenda of human factors science in the intelligence era

This paper proposes the innovative concept of "human factors science" to characterize engineering psychology, human factors engineering, human-computer interaction, and other similar fields. Although the perspectives in these fields differ, they share a common approach: "human-centered design." In the AI era, the human-machine relationship presents a trans-era evolution to "human-AI teaming." The change has raised challenges for human factors science, compelling us to re-examine current research paradigms and agendas. Based on our previous work, this paper proposes three research paradigms: (1) human-AI joint cognitive systems: this regards an intelligent agent as a cognitive agent with a certain level of cognitive capabilities. A human-AI system can be characterized as a joint cognitive system in which humans and intelligent agents work as teammates for collaboration; (2) human-AI joint cognitive ecosystems: an intelligent ecosystem with multiple human-AI systems can be represented as a human-AI joint cognitive ecosystem. The overall performance of the ecosystem depends on optima collaboration and design across the multiple human-AI systems; (3) intelligent sociotechnical systems (iSTS): human-AI systems are design, developed, and deployed in an iSTS environment. The successful design, development, and deployment of a human-AI system within an iSTS environment depends on the synergistic optimization between the subsystems. This paper looks forward to the future research agenda of human factors science from three aspects: human-AI interaction, intelligent human-machine interface, and human-AI teaming. Analyses show that the three new research paradigms will benefit future research in human factors science. We believe the proposed research paradigms and the future research agenda will mutually promote each other, further advancing human factors science in the AI era.

cs.HC↗

arXiv2024

Unified Diffusion-Based Rigid and Non-Rigid Editing with Text and Image Guidance

Existing text-to-image editing methods tend to excel either in rigid or non-rigid editing but encounter challenges when combining both, resulting in misaligned outputs with the provided text prompts. In addition, integrating reference images for control remains challenging. To address these issues, we present a versatile image editing framework capable of executing both rigid and non-rigid edits, guided by either textual prompts or reference images. We leverage a dual-path injection scheme to handle diverse editing scenarios and introduce an integrated self-attention mechanism for fusion of appearance and structural information. To mitigate potential visual artifacts, we further employ latent fusion techniques to adjust intermediate latents. Compared to previous work, our approach represents a significant advance in achieving precise and versatile image editing. Comprehensive experiments validate the efficacy of our method, showcasing competitive or superior results in text-based editing and appearance transfer tasks, encompassing both rigid and non-rigid settings.

cs.CV↗