arXiv subjects

Yifei Xu

Publications and source records attributed to Yifei Xu.

At least 37 records · Page 2Linked to original sources

arXiv2025

Beamforming for Movable and Rotatable Antenna Enabled Multi-User Communications

In the development of wireless communication technology, multiple-input multiple-output (MIMO) technology has emerged as a key enabler, significantly enhancing the capacity of communication systems. However, traditional MIMO systems, which rely on fixed-position antennas (FPAs) with spacing limitations, cannot fully exploit the channel variations in the continuous spatial domain, thus limiting the system's spatial multiplexing performance and diversity. To address these limitations, movable antennas (MAs) have been introduced, offering a breakthrough in signal processing and spatial multiplexing by overcoming the constraints of FPA-based systems. Furthermore, this paper extends the functionality of MAs by introducing movable rotatable antennas (MRAs), which enhance the system's ability to optimize performance in the spatial domain by adding rotational degrees of freedom. By incorporating a dynamic precoding framework based on both antenna position and rotation angle optimization, and employing the zero-forcing (ZF) precoding method, this paper proposes an efficient optimization approach aimed at improving signal quality, mitigating interference, and solving the non-linear, constrained optimization problem using the sequential quadratic programming (SQP) algorithm. This approach effectively enhances the communication system's performance.

eess.SP↗

arXiv2025

CoRNStack: High-Quality Contrastive Data for Better Code Retrieval and Reranking

Effective code retrieval plays a crucial role in advancing code generation, bug fixing, and software maintenance, particularly as software systems increase in complexity. While current code embedding models have demonstrated promise in retrieving code snippets for small-scale, well-defined tasks, they often underperform in more demanding real-world applications such as bug localization within GitHub repositories. We hypothesize that a key issue is their reliance on noisy and inconsistent datasets for training, which impedes their ability to generalize to more complex retrieval scenarios. To address these limitations, we introduce CoRNStack, a large-scale, high-quality contrastive training dataset for code that spans multiple programming languages. This dataset is curated using consistency filtering to eliminate noisy positives and is further enriched with mined hard negatives, thereby facilitating more effective learning. We demonstrate that contrastive training of embedding models using CoRNStack leads to state-of-the-art performance across a variety of code retrieval tasks. Furthermore, the dataset can be leveraged for training code reranking models, a largely underexplored area compared to text reranking. Our finetuned code reranking model significantly improves the ranking quality over the retrieved results. Finally, by employing our code retriever and reranker together, we demonstrate significant improvements in function localization for GitHub issues, an important component of real-world software development.

cs.CL↗

arXiv2024

System States Forecasting of Microservices with Dynamic Spatio-Temporal Data

In the AIOps (Artificial Intelligence for IT Operations) era, accurately forecasting system states is crucial. In microservices systems, this task encounters the challenge of dynamic and complex spatio-temporal relationships among microservice instances, primarily due to dynamic deployments, diverse call paths, and cascading effects among instances. Current time-series forecasting methods, which focus mainly on intrinsic patterns, are insufficient in environments where spatial relationships are critical. Similarly, spatio-temporal graph approaches often neglect the nature of temporal trend, concentrating mostly on message passing between nodes. Moreover, current research in microservices domain frequently underestimates the importance of network metrics and topological structures in capturing the evolving dynamics of systems. This paper introduces STMformer, a model tailored for forecasting system states in microservices environments, capable of handling multi-node and multivariate time series. Our method leverages dynamic network connection data and topological information to assist in modeling the intricate spatio-temporal relationships within the system. Additionally, we integrate the PatchCrossAttention module to compute the impact of cascading effects globally. We have developed a dataset based on a microservices system and conducted comprehensive experiments with STMformer against leading methods. In both short-term and long-term forecasting tasks, our model consistently achieved a 8.6% reduction in MAE(Mean Absolute Error) and a 2.2% reduction in MSE (Mean Squared Error). The source code is available at https://github.com/xuyifeiiie/STMformer.

cs.NI↗

arXiv2024

FIRST: Faster Improved Listwise Reranking with Single Token Decoding

Large Language Models (LLMs) have significantly advanced the field of information retrieval, particularly for reranking. Listwise LLM rerankers have showcased superior performance and generalizability compared to existing supervised approaches. However, conventional listwise LLM reranking methods lack efficiency as they provide ranking output in the form of a generated ordered sequence of candidate passage identifiers. Further, they are trained with the typical language modeling objective, which treats all ranking errors uniformly--potentially at the cost of misranking highly relevant passages. Addressing these limitations, we introduce FIRST, a novel listwise LLM reranking approach leveraging the output logits of the first generated identifier to directly obtain a ranked ordering of the candidates. Further, we incorporate a learning-to-rank loss during training, prioritizing ranking accuracy for the more relevant passages. Empirical results demonstrate that FIRST accelerates inference by 50% while maintaining a robust ranking performance with gains across the BEIR benchmark. Finally, to illustrate the practical effectiveness of listwise LLM rerankers, we investigate their application in providing relevance feedback for retrievers during inference. Our results show that LLM rerankers can provide a stronger distillation signal compared to cross-encoders, yielding substantial improvements in retriever recall after relevance feedback.

cs.IR↗

arXiv2024

Constraining on the non-standard cosmological models combining the observations of high-redshift quasars and BAO

In this work, we studied four types of cosmological models with different mechanisms driving the accelerated expansion of the universe, include Braneworld models, Chaplygin Gas models, Emergent Dark Energy models, and cosmological torsion models. Considering that the dynamics of these models at low redshifts are very similar and difficult to distinguish, we used the latest and largest UV and X-ray measurements of quasars (QSOs) observations covering the range of redshift $0.009<z<7.5$. However, the high intrinsic dispersion of this sample and the degeneracy between cosmological model parameters, we added 2D-BAO and 3D-BAO datasets to help us constrain the parameters of these cosmological models. Our results suggest that standard cold dark matter scenario may not be the best cosmological model preferred by the high-redshift observations. The Generalized Chaplygin Gas (GCG) and cosmological constant plus torsion (named Case II) models perform best by Akaike Information Criterion (AIC), but the $Λ$CDM is the best cosmological model preferred by Bayesian Information Criterion (BIC). Our work also supports that the Phenomenologically Emergent Dark Energy and cosmological torsion models may alleviate the Hubble tension, the reported value of the Hubble constant obtained from QSO+BAO datasets combination lies between Planck 2018 observations and local measurements from the SH0ES collaboration, while other cosmological models all support that the Hubble constant tends to be closer to recent Planck 2018 results, but these model are penalized by information criterion.

astro-ph.CO↗

arXiv2024

Mitigate Target-level Insensitivity of Infrared Small Target Detection via Posterior Distribution Modeling

Infrared Small Target Detection (IRSTD) aims to segment small targets from infrared clutter background. Existing methods mainly focus on discriminative approaches, i.e., a pixel-level front-background binary segmentation. Since infrared small targets are small and low signal-to-clutter ratio, empirical risk has few disturbances when a certain false alarm and missed detection exist, which seriously affect the further improvement of such methods. Motivated by the dense prediction generative methods, in this paper, we propose a diffusion model framework for Infrared Small Target Detection which compensates pixel-level discriminant with mask posterior distribution modeling. Furthermore, we design a Low-frequency Isolation in the wavelet domain to suppress the interference of intrinsic infrared noise on the diffusion noise estimation. This transition from the discriminative paradigm to generative one enables us to bypass the target-level insensitivity. Experiments show that the proposed method achieves competitive performance gains over state-of-the-art methods on NUAA-SIRST, IRSTD-1k, and NUDT-SIRST datasets. Code are available at https://github.com/Li-Haoqing/IRSTD-Diff.

cs.CV↗

arXiv2024

Multiple measurements on the cosmic curvature using Gaussian process regression without calibration and a cosmological model

In this letter, we propose an improved cosmological model-independent method to measure cosmic curvature, combining the recent measurements of transverse and line-of-sight directions in the baryon acoustic oscillations (BAO) with cosmic chronometers (CC) datasets. Considering that the CC dataset is discrete and includes only 32 $H(z)$ measurements, we apply Gaussian process (GP) regression to fit the CC dataset and reconstruct them. Our methodology, which does not need the calibration or selection of any cosmological model, provide multiple measurements of spatial curvature ($Ω_K$) at different redshifts (depending on the redshift coverage of BAO dataset). For combination of all BAO data, we find that the constraint result on cosmic curvature is $Ω_K=-0.096^{+0.190}_{-0.195}$ with $1σ$ observational uncertainty. Although the measured $Ω_K$ is in good agreement with zero cosmic curvature within 1$σ$ confidence level, our result revels the fact of a closed universe. More importantly, our results show that the obtained $Ω_K$ measurements are almost unaffected by different priors of the Hubble constant. This could help solve the issue of the Hubble tension that may be caused by inconsistencies in the spatial curvature between the early and late universes.

astro-ph.CO↗

arXiv2023

CloudEval-YAML: A Practical Benchmark for Cloud Configuration Generation

Among the thriving ecosystem of cloud computing and the proliferation of Large Language Model (LLM)-based code generation tools, there is a lack of benchmarking for code generation in cloud-native applications. In response to this need, we present CloudEval-YAML, a practical benchmark for cloud configuration generation. CloudEval-YAML tackles the diversity challenge by focusing on YAML, the de facto standard of numerous cloud-native tools. We develop the CloudEval-YAML benchmark with practicality in mind: the dataset consists of hand-written problems with unit tests targeting practical scenarios. We further enhanced the dataset to meet practical needs by rephrasing questions in a concise, abbreviated, and bilingual manner. The dataset consists of 1011 problems that take more than 1200 human hours to complete. To improve practicality during evaluation, we build a scalable evaluation platform for CloudEval-YAML that achieves a 20 times speedup over a single machine. To the best of our knowledge, the CloudEval-YAML dataset is the first hand-written dataset targeting cloud-native applications. We present an in-depth evaluation of 12 LLMs, leading to a deeper understanding of the problems and LLMs, as well as effective methods to improve task performance and reduce cost.

cs.DC↗

arXiv2023

Click on Mask: A Labor-efficient Annotation Framework with Level Set for Infrared Small Target Detection

Infrared Small Target Detection is a challenging task to separate small targets from infrared clutter background. Recently, deep learning paradigms have achieved promising results. However, these data-driven methods need plenty of manual annotation. Due to the small size of infrared targets, manual annotation consumes more resources and restricts the development of this field. This letter proposed a labor-efficient and cursory annotation framework with level set, which obtains a high-quality pseudo mask with only one cursory click. A variational level set formulation with an expectation difference energy functional is designed, in which the zero level contour is intrinsically maintained during the level set evolution. It solves the issue that zero level contour disappearing due to small target size and excessive regularization. Experiments on the NUAA-SIRST and IRSTD-1k datasets reveal that our approach achieves superior performance. Code is available at https://github.com/Li-Haoqing/COM.

cs.CV↗

arXiv2023

ILNet: Low-level Matters for Salient Infrared Small Target Detection

Infrared small target detection is a technique for finding small targets from infrared clutter background. Due to the dearth of high-level semantic information, small infrared target features are weakened in the deep layers of the CNN, which underachieves the CNN's representation ability. To address the above problem, in this paper, we propose an infrared low-level network (ILNet) that considers infrared small targets as salient areas with little semantic information. Unlike other SOTA methods, ILNet pays greater attention to low-level information instead of treating them equally. A new lightweight feature fusion module, named Interactive Polarized Orthogonal Fusion module (IPOF), is proposed, which integrates more important low-level features from the shallow layers into the deep layers. A Dynamic One-Dimensional Aggregation layers (DODA) are inserted into the IPOF, to dynamically adjust the aggregation of low dimensional information according to the number of input channels. In addition, the idea of ensemble learning is used to design a Representative Block (RB) to dynamically allocate weights for shallow and deep layers. Experimental results on the challenging NUAA-SIRST (78.22% nIoU and 1.33e-6 Fa) and IRSTD-1K (68.91% nIoU and 3.23e-6 Fa) dataset demonstrate that the proposed ILNet can get better performances than other SOTA methods. Moreover, ILNet can obtain a greater improvement with the increasement of data volume. Training code are available at https://github.com/Li-Haoqing/ILNet.

cs.CV↗

arXiv2023

Smart Meters Integration in Distribution System State Estimation with Collaborative Filtering and Deep Gaussian Process

The problem of state estimations for electric distribution system is considered. A collaborative filtering approach is proposed in this paper to integrate the slow time-scale smart meter measurements in the distribution system state estimation, in which the deep Gaussian process is incorporated to infer the fast time-scale pseudo measurements and avoid anomalies. Numerical tests have demonstrated the higher estimation accuracy of the proposed method.

eess.SY↗

arXiv2023

Radiation-induced Acoustic Signal Denoising using a Supervised Deep Learning Framework for Imaging and Therapy Monitoring

Radiation-induced acoustic (RA) imaging is a promising technique for visualizing radiation energy deposition in tissues, enabling new imaging modalities and real-time therapy monitoring. However, it requires measuring hundreds or even thousands of averages to achieve satisfactory signal-to-noise ratios (SNRs). This repetitive measurement increases ionizing radiation dose and degrades the temporal resolution of RA imaging, limiting its clinical utility. In this study, we developed a general deep inception convolutional neural network (GDI-CNN) to denoise RA signals to substantially reduce the number of averages. The multi-dilation convolutions in the network allow for encoding and decoding signal features with varying temporal characteristics, making the network generalizable to signals from different radiation sources. The proposed method was evaluated using experimental data of X-ray-induced acoustic, protoacoustic, and electroacoustic signals, qualitatively and quantitatively. Results demonstrated the effectiveness and generalizability of GDI-CNN: for all the enrolled RA modalities, GDI-CNN achieved comparable SNRs to the fully-averaged signals using less than 2% of the averages, significantly reducing imaging dose and improving temporal resolution. The proposed deep learning framework is a general method for few-frame-averaged acoustic signal denoising, which significantly improves RA imaging's clinical utilities for low-dose imaging and real-time therapy monitoring.

physics.med-ph↗

arXiv2023

A Tale of Two Latent Flows: Learning Latent Space Normalizing Flow with Short-run Langevin Flow for Approximate Inference

We study a normalizing flow in the latent space of a top-down generator model, in which the normalizing flow model plays the role of the informative prior model of the generator. We propose to jointly learn the latent space normalizing flow prior model and the top-down generator model by a Markov chain Monte Carlo (MCMC)-based maximum likelihood algorithm, where a short-run Langevin sampling from the intractable posterior distribution is performed to infer the latent variables for each observed example, so that the parameters of the normalizing flow prior and the generator can be updated with the inferred latent variables. We show that, under the scenario of non-convergent short-run MCMC, the finite step Langevin dynamics is a flow-like approximate inference model and the learning objective actually follows the perturbation of the maximum likelihood estimation (MLE). We further point out that the learning framework seeks to (i) match the latent space normalizing flow and the aggregated posterior produced by the short-run Langevin flow, and (ii) bias the model from MLE such that the short-run Langevin flow inference is close to the true posterior. Empirical results of extensive experiments validate the effectiveness of the proposed latent space normalizing flow model in the tasks of image generation, image reconstruction, anomaly detection, supervised image inpainting and unsupervised image recovery.

stat.ML↗

arXiv2023

SAS: Self-Augmentation Strategy for Language Model Pre-training

The core of self-supervised learning for pre-training language models includes pre-training task design as well as appropriate data augmentation. Most data augmentations in language model pre-training are context-independent. A seminal contextualized augmentation was recently proposed in ELECTRA and achieved state-of-the-art performance by introducing an auxiliary generation network (generator) to produce contextualized data augmentation for the training of a main discrimination network (discriminator). This design, however, introduces extra computation cost of the generator and a need to adjust the relative capability between the generator and the discriminator. In this paper, we propose a self-augmentation strategy (SAS) where a single network is utilized for both regular pre-training and contextualized data augmentation for the training in later epochs. Essentially, this strategy eliminates a separate generator and uses the single network to jointly conduct two pre-training tasks with MLM (Masked Language Modeling) and RTD (Replaced Token Detection) heads. It avoids the challenge to search for an appropriate size of the generator, which is critical to the performance as evidenced in ELECTRA and its subsequent variant models. In addition, SAS is a general strategy that can be seamlessly combined with many new techniques emerging recently or in the future, such as the disentangled attention mechanism from DeBERTa. Our experiments show that SAS is able to outperform ELECTRA and other state-of-the-art models in the GLUE tasks with similar or less computation cost.

cs.CL↗

arXiv2022

Sound2Synth: Interpreting Sound via FM Synthesizer Parameters Estimation

Synthesizer is a type of electronic musical instrument that is now widely used in modern music production and sound design. Each parameters configuration of a synthesizer produces a unique timbre and can be viewed as a unique instrument. The problem of estimating a set of parameters configuration that best restore a sound timbre is an important yet complicated problem, i.e.: the synthesizer parameters estimation problem. We proposed a multi-modal deep-learning-based pipeline Sound2Synth, together with a network structure Prime-Dilated Convolution (PDC) specially designed to solve this problem. Our method achieved not only SOTA but also the first real-world applicable results on Dexed synthesizer, a popular FM synthesizer.

cs.SD↗

arXiv2022

Energy-Based Continuous Inverse Optimal Control

The problem of continuous inverse optimal control (over finite time horizon) is to learn the unknown cost function over the sequence of continuous control variables from expert demonstrations. In this article, we study this fundamental problem in the framework of energy-based model, where the observed expert trajectories are assumed to be random samples from a probability density function defined as the exponential of the negative cost function up to a normalizing constant. The parameters of the cost function are learned by maximum likelihood via an "analysis by synthesis" scheme, which iterates (1) synthesis step: sample the synthesized trajectories from the current probability density using the Langevin dynamics via back-propagation through time, and (2) analysis step: update the model parameters based on the statistical difference between the synthesized trajectories and the observed trajectories. Given the fact that an efficient optimization algorithm is usually available for an optimal control problem, we also consider a convenient approximation of the above learning method, where we replace the sampling in the synthesis step by optimization. Moreover, to make the sampling or optimization more efficient, we propose to train the energy-based model simultaneously with a top-down trajectory generator via cooperative learning, where the trajectory generator is used to fast initialize the synthesis step of the energy-based model. We demonstrate the proposed methods on autonomous driving tasks, and show that they can learn suitable cost functions for optimal control.

cs.LG↗

arXiv2022

Analytical Research on a Locally Resonant Periodic Foundation for Mitigating Structure-Borne Vibrations from Subway

Filtering properties of locally resonant periodic foundations (LRPFs) have inspired an innovative direction towards the mitigation of structural vibrations. To mitigate the structure-borne vibrations from subways, this study proposes an LRPF equipped with a negative stiffness device connecting the resonator and primary structure. The proposed LRPF can exhibit a quasi-static band gap covering the ultra-low frequency range. These frequency components have the properties of strong diffraction and low attenuation and contribute the most to the incident wave fields impinging on nearby buildings. By formulating the interaction problem between the tunnel-ground and LRPF-superstructure systems, the mitigation performance of the proposed LRPF is evaluated considering the effects of soil compliance and superstructure. The performance depends on the dynamic properties of the ground, foundation, and superstructure as well as their coupling. Transmission analyses indicate that the superstructure responses can be effectively attenuated in the quasi-static band gap by adjusting the negative stiffness. Considering the coupling of the flexible ground, the peak responses of the LRPF-superstructure system occur not only at its eigenfrequencies but also at coupled resonance frequencies due to the contribution of the soil compliance. This study provides an analytical tool for mitigating the structure-borne vibrations from subways with the LRPF.

physics.app-ph↗

arXiv2021

Size-adjustable Ring-shape Photoacoustic Tomography System

Photoacoustic tomography (PAT) combines the advantages of the spectroscopic optical absorption contrast and acoustic resolution with deep penetration, and becomes an important novel biomedical imaging technology for scientific research and clinical diagnosis. In this paper, an imaging size-adjustable PAT system is proposed for clinical applications, which can adapt for different size imaging targets. Comparing with the conventional PAT system setup which with a fixed radius ring shape ultrasound transducer (UT) array, the proposed system, which is based on sectorial ultrasound transducer array (SUTA), is more flexible for different size targets imaging. There are 32 elements for each SUTA, and four SUTAs form a 128-channel UT array for photoacoustic wave detection. The four SUTAs are controlled by four stepper motors, and change the SUTAs distribute positon that adapt for imaging applications. The radius of the proposed system imaging region of interest (ROI) can be adjusted from 50 mm to 90 mm, which is much more flexible than the conventional full ring UT array PAT system. The simulation results generated by the MATLAB k-wave toolbox very well demonstrate the feasibility of the proposed system. To further validate the proposed system for size-adjustable imaging, a vascular mimicking phantom and ex-vivo pork breast with indocyanine green (ICG) injected are imaged to prove its feasibility for clinical applications.

physics.ins-det↗