arXiv subjects

Fangyu Li

Publications and source records attributed to Fangyu Li.

18 recordsLinked to original sources

arXiv2026

Fully Distributed Multi-View 3D Tracking in Real-Time

Multi-camera tracking with overlapping fields of view typically relies on centralized fusion, which creates computational bottlenecks that prevent deployment at scale. We present MV3DT, a fully distributed framework for real-time multi-view 3D tracking that achieves accurate identity propagation and occlusion recovery through peer-to-peer coordination, eliminating the need for central aggregation. Each camera node executes a lightweight modular pipeline comprising monocular 3D perception, distributed multi-view association, and collaborative fusion via lightweight messaging. MV3DT achieves 96.5% IDF1, 93.1% MOTA, and 94.6% MOTP on WILDTRACK, competitive with state-of-the-art centralized methods, and unprecedented 41.7% IDF1 and 50.9% MOTA on SCOUT while demonstrating superior scalability: sustaining 30 FPS on 100 cameras with <10ms inter-camera latency and only 2.2% communication overhead. MV3DT operates in a zero-shot regime given camera calibrations, requiring no scene-specific learning and making it directly deployable in new environments. These results establish MV3DT as a practical solution for real-time multi-view tracking in large-scale overlapping camera networks.

cs.CV↗

arXiv2025

Robust Multimodal Semantic Segmentation with Balanced Modality Contributions

Multimodal semantic segmentation enhances model robustness by exploiting cross-modal complementarities. However, existing methods often suffer from imbalanced modal dependencies, where overall performance degrades significantly once a dominant modality deteriorates in real-world scenarios. Thus, modality balance has become acritical challenge for practical multimodal segmentation. To address this issue, we propose EQUISeg, a multimodal segmentation framework that balances modality contributions through equal encoding of modalities. Built upon a four-stage Cross-modal Transformer Block(CMTB), EQUISeg enables efficient multimodal fusion and hierarchical selection. Furthermore, we design a Self-guided Module(SGM) that mitigates modality imbalance by introducing a mutual guidance mechanism, enabling each modality to adaptively adjust its contribution and enhance robustness under degraded conditions. Extensive experiments on multiple datasets demonstrate that EQUISeg achieves significant performance gains and effectively alleviates the adverse effects of modality imbalance in segmentation tasks.

cs.CV↗

arXiv2025

Instruction Guided Multi Object Image Editing with Quantity and Layout Consistency

Instruction driven image editing with standard CLIP text encoders often fails in complex scenes with many objects. We present QL-Adapter, a framework for multiple object editing that tackles two challenges: enforcing object counts and spatial layouts, and accommodating diverse categories. QL-Adapter consists of two core modules: the Image-Layout Fusion Module (ILFM) and the Cross-Modal Augmentation Module (CMAM). ILFM fuses layout priors with ViT patch tokens from the CLIP image encoder to strengthen spatial structure understanding. CMAM injects image features into the text branch to enrich textual embeddings and improve instruction following. We further build QL-Dataset, a benchmark that spans broad category, layout, and count variations, and define the task of quantity and layout consistent image editing (QL-Edit). Extensive experiments show that QL-Adapter achieves state of the art performance on QL-Edit and significantly outperforms existing models.

cs.CV↗

arXiv2025

The constraints on the stochastic gravitational wave background from cosmic strings by an electromagnetic resonance system

As one of the primary detection targets for contemporary gravitational wave (GW) observatories, the stochastic gravitational wave background (SGWB) holds significant potential for enhancing our understanding of the early universe's formation and evolution. Studies indicate that the SGWB spectrum from cosmic strings can span an extraordinarily broad frequency range, extending from extremely low frequencies up to the microwave band. This work specifically investigates the detectability of cosmic string SGWB signals in an electromagnetic (EM) resonance system at GHz frequency. We present a systematic analysis encompassing: (1) the response of high frequency gravitational waves (HFGWs) in such EM resonance system. (2) the development and application of fundamental data processing protocols in the EM resonance system. Our results demonstrate that the EM system shows promising sensitivity to detect cosmic string SGWB signals with tension parameters $G\mu\geq 10^{-11}$ (the corresponding dimensionless amplitude $h \geq 10^{-33}$ at 1 GHz), while potentially establishing new constraints for $G\mu\leq 10^{-11}$ in the microwave band. These findings would complement existing multi-band SGWB observations and provide additional constraints on cosmic-string tension parameters in GHz frequency regimes.

gr-qc↗

arXiv2025

Generation of 95-qubit genuine entanglement and verification of symmetry-protected topological phases

Symmetry-protected topological (SPT) phases are fundamental features of cluster states, serving as key resources for measurement-based quantum computation (MBQC). Generating large-scale cluster states and verifying their SPT phases are essential steps toward practical MBQC, which however still presents significant experimental challenges. In this work, we address these challenges by utilizing advanced superconducting hardware with optimized gate operations, enhanced readout fidelity, and error mitigation techniques. We successfully generate and verify 95-qubit one-dimensional and 72-qubit two-dimensional genuine entangled cluster states, achieving fidelities of $0.5603 \pm 0.0084$ and $0.5519 \pm 0.0054$, respectively. Leveraging these high-fidelity cluster states, we investigate SPT phases through quantum teleportation across all 95 qubits and demonstrate input-state-dependent robustness against symmetry-breaking perturbations, highlighting the practicality and intrinsic robustness of MBQC enabled by the SPT order. Our results represent a significant advancement in large-scale entanglement generation and topological phase simulation, laying the foundation for scalable and practical MBQC using superconducting quantum systems.

quant-ph↗

arXiv2024

Establishing a New Benchmark in Quantum Computational Advantage with 105-qubit Zuchongzhi 3.0 Processor

In the relentless pursuit of quantum computational advantage, we present a significant advancement with the development of Zuchongzhi 3.0. This superconducting quantum computer prototype, comprising 105 qubits, achieves high operational fidelities, with single-qubit gates, two-qubit gates, and readout fidelity at 99.90%, 99.62% and 99.18%, respectively. Our experiments with an 83-qubit, 32-cycle random circuit sampling on Zuchongzhi 3.0 highlight its superior performance, achieving one million samples in just a few hundred seconds. This task is estimated to be infeasible on the most powerful classical supercomputers, Frontier, which would require approximately $6.4\times 10^9$ years to replicate the task. This leap in processing power places the classical simulation cost six orders of magnitude beyond Google's SYC-67 and SYC-70 experiments [Nature 634, 328(2024)], firmly establishing a new benchmark in quantum computational advantage. Our work not only advances the frontiers of quantum computing but also lays the groundwork for a new era where quantum processors play an essential role in tackling sophisticated real-world challenges.

quant-ph↗

arXiv2023

Improving Sequential Recommendation Models with an Enhanced Loss Function

There has been a growing interest in benchmarking sequential recommendation models and reproducing/improving existing models. For example, Rendle et al. improved matrix factorization models by tuning their parameters and hyperparameters. Petrov and Macdonald developed a more efficient and effective implementation of BERT4Rec, which resolved inconsistencies in performance comparison between BERT4Rec and SASRec in previous works. In particular, BERT4Rec and SASRec share a similar network structure, with the main difference lying in their training objective/loss function. Therefore, we analyzed the advantages and disadvantages of commonly used loss functions in sequential recommendation and proposed an improved loss function that leverages their strengths. We conduct extensive experiments on two influential open-source libraries, and the results demonstrate that our improved loss function significantly enhances the performance of GRU4Rec, SASRec, SR-GNN, and S3Rec models, improving their benchmarks significantly. Furthermore, the improved SASRec benchmark outperforms BERT4Rec on the ML-1M and Beauty datasets and achieves similar results to BERT4Rec on the ML-20M and Steam datasets. We also reproduce the results of the BERT4Rec model on the Beauty dataset. Finally, we provide a comprehensive explanation of the effectiveness of our improved loss function through experiments. Our code is publicly available at https://github.com/Li-fAngyU/sequential_rec.

cs.IR↗

arXiv2022

CPS Attack Detection under Limited Local Information in Cyber Security: A Multi-node Multi-class Classification Ensemble Approach

Cybersecurity breaches are the common anomalies for distributed cyber-physical systems (CPS). However, the cyber security breach classification is still a difficult problem, even using cutting-edge artificial intelligence (AI) approaches. In this paper, we study the multi-class classification problem in cyber security for attack detection. A challenging multi-node data-censoring case is considered. In such a case, data within each data center/node cannot be shared while the local data is incomplete. Particularly, local nodes contain only a part of the multiple classes. In order to train a global multi-class classifier without sharing the raw data across all nodes, the main result of our study is designing a multi-node multi-class classification ensemble approach. By gathering the estimated parameters of the binary classifiers and data densities from each local node, the missing information for each local node is completed to build the global multi-class classifier. Numerical experiments are given to validate the effectiveness of the proposed approach under the multi-node data-censoring case. Under such a case, we even show the out-performance of the proposed approach over the full-data approach.

cs.CR↗

arXiv2020

Machine Learning Research Towards Combating COVID-19: Virus Detection, Spread Prevention, and Medical Assistance

COVID-19 was first discovered in December 2019 and has continued to rapidly spread across countries worldwide infecting thousands and millions of people. The virus is deadly, and people who are suffering from prior illnesses or are older than the age of 60 are at a higher risk of mortality. Medicine and Healthcare industries have surged towards finding a cure, and different policies have been amended to mitigate the spread of the virus. While Machine Learning (ML) methods have been widely used in other domains, there is now a high demand for ML-aided diagnosis systems for screening, tracking, and predicting the spread of COVID-19 and finding a cure against it. In this paper, we present a journey of what role ML has played so far in combating the virus, mainly looking at it from a screening, forecasting, and vaccine perspectives. We present a comprehensive survey of the ML algorithms and models that can be used on this expedition and aid with battling the virus.

cs.CY↗

arXiv2020

Learning from Unlabelled Videos Using Contrastive Predictive Neural 3D Mapping

Predictive coding theories suggest that the brain learns by predicting observations at various levels of abstraction. One of the most basic prediction tasks is view prediction: how would a given scene look from an alternative viewpoint? Humans excel at this task. Our ability to imagine and fill in missing information is tightly coupled with perception: we feel as if we see the world in 3 dimensions, while in fact, information from only the front surface of the world hits our retinas. This paper explores the role of view prediction in the development of 3D visual recognition. We propose neural 3D mapping networks, which take as input 2.5D (color and depth) video streams captured by a moving camera, and lift them to stable 3D feature maps of the scene, by disentangling the scene content from the motion of the camera. The model also projects its 3D feature maps to novel viewpoints, to predict and match against target views. We propose contrastive prediction losses to replace the standard color regression loss, and show that this leads to better performance on complex photorealistic data. We show that the proposed model learns visual representations useful for (1) semi-supervised learning of 3D object detectors, and (2) unsupervised learning of 3D moving object detectors, by estimating the motion of the inferred 3D feature maps in videos of dynamic scenes. To the best of our knowledge, this is the first work that empirically shows view prediction to be a scalable self-supervised task beneficial to 3D object detection.

cs.CV↗

arXiv2019

PoTrojan: powerful neural-level trojan designs in deep learning models

With the popularity of deep learning (DL), artificial intelligence (AI) has been applied in many areas of human life. Neural network or artificial neural network (NN), the main technique behind DL, has been extensively studied to facilitate computer vision and natural language recognition. However, the more we rely on information technology, the more vulnerable we are. That is, malicious NNs could bring huge threat in the so-called coming AI era. In this paper, for the first time in the literature, we propose a novel approach to design and insert powerful neural-level trojans or PoTrojan in pre-trained NN models. Most of the time, PoTrojans remain inactive, not affecting the normal functions of their host NN models. PoTrojans could only be triggered in very rare conditions. Once activated, however, the PoTrojans could cause the host NN models to malfunction, either falsely predicting or classifying, which is a significant threat to human society of the AI era. We would explain the principles of PoTrojans and the easiness of designing and inserting them in pre-trained deep learning models. PoTrojans doesn't modify the existing architecture or parameters of the pre-trained models, without re-training. Hence, the proposed method is very efficient.

cs.CR↗

arXiv2018

Toward Creating Subsurface Camera

In this article, the framework and architecture of Subsurface Camera (SAMERA) is envisioned and described for the first time. A SAMERA is a geophysical sensor network that senses and processes geophysical sensor signals, and computes a 3D subsurface image in-situ in real-time. The basic mechanism is: geophysical waves propagating/reflected/refracted through subsurface enter a network of geophysical sensors, where a 2D or 3D image is computed and recorded; a control software may be connected to this network to allow view of the 2D/3D image and adjustment of settings such as resolution, filter, regularization and other algorithm parameters. System prototypes based on seismic imaging have been designed. SAMERA technology is envisioned as a game changer to transform many subsurface survey and monitoring applications, including oil/gas exploration and production, subsurface infrastructures and homeland security, wastewater and CO2 sequestration, earthquake and volcano hazard monitoring. The system prototypes for seismic imaging have been built. Creating SAMERA requires an interdisciplinary collaboration and transformation of sensor networks, signal processing, distributed computing, and geophysical imaging.

eess.SP↗

arXiv2018

Network Phenotyping for Network Traffic Classification and Anomaly Detection

This paper proposes to develop a network phenotyping mechanism based on network resource usage analysis and identify abnormal network traffic. The network phenotyping may use different metrics in the cyber physical system (CPS), including resource and network usage monitoring, physical state estimation. The set of devices will collectively decide a holistic view of the entire system through advanced image processing and machine learning methods. In this paper, we choose the network traffic pattern as a study case to demonstrate the effectiveness of the proposed method, while the methodology may similarly apply to classification and anomaly detection based on other resource metrics. We apply image processing and machine learning on the network resource usage to extract and recognize communication patterns. The phenotype method is experimented on four real-world decentralized applications. With proper length of sampled continuous network resource usage, the overall recognition accuracy is about 99%. Additionally, the recognition error is used to detect the anomaly network traffic. We simulate the anomaly network resource usage that equals to 10%, 20% and 30% of the normal network resource usage. The experiment results show the proposed anomaly detection method is efficient in detecting each intensity of anomaly network resource usage.

cs.NI↗

arXiv2017

Quasi-B-mode generated by high-frequency gravitational waves and corresponding perturbative photon fluxes

Interaction of very low-frequency primordial(relic) gravitational waves(GWs) to cosmic microwave background(CMB) can generate B-mode polarization. Here, for the first time we point out that the electromagnetic(EM) response to high-frequency GWs(HFGWs) would produce quasi-B-mode distribution of the perturbative photon fluxes, and study the duality and high complementarity between such two B-modes. Based on this quasi-B-mode in HFGWs, it is shown that the distinguishing and observing of HFGWs from the braneworld would be quite possible due to their large amplitude, higher frequency and very different physical behaviors between the perturbative photon fluxes and background photons, and the measurement of relic HFGWs may also be possible though face to enormous challenge.

gr-qc↗

arXiv2016

Very high frequency gravitational waves from magnetars and gamma-ray burst

Extremely powerful astrophysical electromagnetic (EM) system could be possible source of high-frequency gravitational waves (HFGWs). Here based on properties of magnetars and gamma-ray bursts (GRBs), we address "Gamma-HFGWs" (with very high-frequency around 10^{20}Hz) caused by ultra-strong EM radiations (in the radiation-dominated phase of GRBs fireball) interacting with super-high magnetar surface magnetic fields (around 10^{11}Tesla). By certain parameters of distance and power, the Gamma-HFGWs would have far field energy density around 10^{-6}, and they would cause perturbed signal EM waves of around 10^{-20}Watt/m^2 in planned HFGW detection system based on EM response to GWs. Specially, Gamma-HFGWs would possess distinctive envelopes with characteristic shapes depending on the particular structures of surface magnetic fields of magnetars, which could be exclusive features helpful to distinguish them from background noise. Results obtained suggest that magnetars could involve in possible astrophysical EM sources of GWs in very high-frequency band, and Gamma-HFGWs would be potential targets for observations in the future.

gr-qc↗

arXiv2008

Perturbative Photon Fluxes Generated by High-Frequency Gravitational Waves and Their Physical Effects

We consider the electromagnetic (EM) perturbative effects produced by the high-frequency gravitational waves (HFGWs) in the GHz band in a special EM resonance system, which consists of fractal membranes, a Gaussian beam (GB) passing through a static magnetic field. It is predicted, under the synchroresonance condition, coherence modulation of the HFGWs to the preexisting transverse components of the GB produces the transverse perturbative photon flux (PPF),which has three novel and important properties: (1)The PPF has maximum at a longitudinal symmetrical surface of the GB where the transverse background photon flux (BPF) vanishes; (2) the resonant effect will be high sensitive to the propagating directions of the HFGWs; (3) the PPF reflected or transmitted by the fractal membrane exhibits a very small decay compared with very large decay of the much stronger BPF. Such properties might provide a new way to distinguish and display the perturbative effects produced by the HFGWs. We also discuss the high-frequency asymptotic behavior of the relic GWs in the microwave band and the positive definite issues of their energy-momentum pseudo-tensor.

gr-qc↗

arXiv2006

Perturbative photon flux generated by high-frequency relic gravitational waves and utilization of them for their detection

There exist corresponding metric perturbations of the relic gravitational waves (GWs) in the region of approximately h~10^(-30)-10^(-32)in the GHz band. A detector for these GWs is described in which we measure the perturbative photon flux (PPF) or signal generated by such high-frequency relic GWs (HFRGWs) via a coupling system of fractal membranes and a Gaussian beam (GB) passing through a static magnetic field. It is found that under the synchro-resonance condition in which the frequency of the GB is set equal to the frequency of the expected HFRGWs (h~2.00*10^(-31), v_g=10^10Hz in the quintessential inflationary models (QIM) and h~6.32*10^(-31), v_g=10^10Hz in the pre-big bang scenario (PBBS) may produce the PPFs of ~4.04*10^2/s and ~1.27*10^3/s in a surface of 100cm^2 area at the waist of the GB, respectively. The relatively weak first-order PPF, directed at right angles to the expected HFRGWs, is reflected by fractal membrane and the resulting reflected PPF (signal) exhibits a very small decay in transit to the detector (tunable microwave receiver) compared with the much stronger background photon flux, which allows for detection of the reflected PPF with signal to background noise ratios greater than one at the distance of the detector. We also discuss the selection capability of system and directional sensitivity for the resonance components from the stochastic relic GW background. The resolution of tiny difference between the PPFs generated by the relic GWs in the QIM and in the PBBS may be established and will be of cosmological significance. PACS numbers: 04.30.Nk, 04.30.Db, and 98.80.Cq.

gr-qc↗

arXiv2005

Utilization of electromagnetic detector for selection and detection of high-frequency relic gravitational waves

It is shown that coupling system between fractal membranes and a Gaussian beam passing through a static magnetic field has strong selection capability for the stochastic relic gravitational wave background. The relic GW components propagating along the positive direction of the symmetrical axis of the Gaussian beam might generate an optimal electromagnetic perturbation while the perturbation produced by the relic GW components propagating along the negative and perpendicular directions to the symmetrical axis will be much less than the former.The influence of the random fluctuation of the relic GWs to such effect can be neglected and the influence of the random fluctuation of the relic GWs to such effect can be neglected.

gr-qc↗