arXiv subjects

Shuang Zheng

Publications and source records attributed to Shuang Zheng.

18 recordsLinked to original sources

arXiv2026

Beam Hopping Low Earth Orbit Satellite Resource Allocation for Differentiated Services and Robustness Analysis under Model Attacks

Beam hopping (BH)-enabled Low Earth Orbit (LEO) satellites play a pivotal role in next-generation communication networks by providing global coverage, improving spectrum efficiency, and supporting flexible adaptation to heterogeneous service demands. To fully exploit these capabilities, artificial intelligence (AI) techniques are increasingly employed for dynamic resource allocation and power management. However, limited onboard resources and potential adversarial perturbations pose challenges to both efficiency and robustness. To address these issues, we leverage digital twin technology to accurately capture the spatio-temporal dynamics of user-satellite visibility, thereby providing precise state information for decision-making. Building on this, we formulate a joint optimization framework for BH scheduling and power allocation as a Markov Decision Process and propose BRIDGE, i.e., BH with Reinforcement learning incorporating Integrated Dirichlet and Gumbel-TopK Exploration, which integrates a quality of service (QoS)-driven subchannel scheduling mechanism to ensure efficient and differentiated resource allocation. The robustness of the model is systematically evaluated under three classical adversarial attacks. Simulation results demonstrate that the proposed approach achieves superior energy efficiency, service throughput, and fairness, while the robustness analysis shows stable performance under the considered bounded adversarial perturbations.

cs.NI↗

arXiv2026

ReinPath: A Multimodal Reinforcement Learning Approach for Pathology

Interpretability is significant in computational pathology, leading to the development of multimodal information integration from histopathological image and corresponding text data.However, existing multimodal methods have limited interpretability due to the lack of high-quality dataset that support explicit reasoning and inference and simple reasoning process.To address the above problems, we introduce a novel multimodal pathology large language model with strong reasoning capabilities.To improve the generation of accurate and contextually relevant textual descriptions, we design a semantic reward strategy integrated with group relative policy optimization.We construct a high-quality pathology visual question answering (VQA) dataset, specifically designed to support complex reasoning tasks.Comprehensive experiments conducted on this dataset demonstrate that our method outperforms state-of-the-art methods, even when trained with only 20% of the data.Our method also achieves comparable performance on downstream zero-shot image classification task compared with CLIP.

cs.CV↗

arXiv2025

Photonic chip-based Reconfigurable Radar Compound Jamming Signal Generator

Microwave photonics (MWP) serves as a powerful bridge between the radio-frequency and optical worlds, unlocking unprecedented bandwidth and speed for critical information systems. Recently, MWP-based radar jamming has demonstrated significant potential in overcoming electronic bottlenecks; however, existing solutions rely heavily on bulky discrete components and generate deterministic symmetric waveforms that are vulnerable to advanced counter-countermeasures. Here, we break this status quo by demonstrating the first monolithic photonic chip-based reconfigurable radar compound jamming signal generator. Implemented on a compact 25 mm2 silicon photonic footprint, our system features high integration and electrical reconfigurability, supporting agile switching among four distinct jamming modes. Crucially, we introduce a composite jamming mechanism that exploits time-frequency coupling to break the inherent symmetry of traditional deceptive jamming, generating controllable asymmetric false-target clusters. The on-chip system exhibits an operating bandwidth exceeding 20 GHz and is capable of generating over 20 high-fidelity false targets simultaneously. This work establishes a fully functional platform combining broad bandwidth, multi-mode flexibility, and asymmetric deception, paving the way for miniaturized, intelligent photonic solutions in next-generation electronic warfare.

physics.optics↗

arXiv2025

Fully Tunable On-Chip Meta-Generator for Multidimensional Poincaré Sphere mapping

The angular momentum of light can be elegantly mapped onto high-order Poincare spheres, providing a powerful framework for describing structured light beams. Such beams have shown extraordinary potential across diverse applications, including high-capacity optical communications, precision metrology, and quantum information processing. While various methods exist for generating structured light beams, the dynamic synthesis and flexible control of arbitrary vectorial states on diverse, multidimensional Poincare spheres still rely on bulky free-space optical components, posing significant challenges for scalability and integration. To date, a fully tunable solution implemented on a single photonic chip has yet to be realized. Here, we present the first fully tunable on-chip meta-generator capable of dynamically mapping arbitrary scalar, vectorial, and hybrid modes onto the full hierarchy of Poincare spheres, and even extending to a high-dimensional Poincare hypersphere within a four-dimensional Hilbert space. Our device is implemented on an eight-channel space-multiplexed multimode silicon photonic integrated circuit, where densely integrated mode multiplexers, amplitude-phase modulators, and an inverse-designed multimode meta-waveguide together enable compact, precise, and programmable control of structured light. The multimode meta-waveguide directly maps eight on-chip guided modes to orbital angular momentum (OAM), supporting broadband generation of high-purity OAM modes with diverse polarization states and topological charges. By simultaneously engineering amplitude, phase, polarization, and topological charge, we achieve full-field control over OAM mode bases, enabling fully tunable access to arbitrary scalar and vectorial states across more than eight distinct Poincare spheres.

physics.optics↗

arXiv2024

Link Prediction on Textual Edge Graphs

Textual-edge Graphs (TEGs), characterized by rich text annotations on edges, are increasingly significant in network science due to their ability to capture rich contextual information among entities. Existing works have proposed various edge-aware graph neural networks (GNNs) or let language models directly make predictions. However, they often fall short of fully capturing the contextualized semantics on edges and graph topology, respectively. This inadequacy is particularly evident in link prediction tasks that require a comprehensive understanding of graph topology and semantics between nodes. In this paper, we present a novel framework - Link2Doc, designed especially for link prediction on textual-edge graphs. Specifically, we propose to summarize neighborhood information between node pairs as a human-written document to preserve both semantic and topology information. A self-supervised learning model is then utilized to enhance GNN's text-understanding ability from language models. Empirical evaluations, including link prediction, edge classification, parameter analysis, runtime comparison, and ablation studies, on four real-world datasets demonstrate that Link2Doc achieves generally better performance against existing edge-aware GNNs and pre-trained language models in predicting links on TEGs.

cs.SI↗

arXiv2024

Sustainable Wireless Networks via Reconfigurable Intelligent Surfaces (RISs): Overview of the ETSI ISG RIS

Reconfigurable Intelligent Surfaces (RISs) are a novel form of ultra-low power devices that are capable to increase the communication data rates as well as the cell coverage in a cost- and energy-efficient way. This is attributed to their programmable operation that enables them to dynamically manipulate the wireless propagation environment, a feature that has lately inspired numerous research investigations and applications. To pave the way to the formal standardization of RISs, the European Telecommunications Standards Institute (ETSI) launched the Industry Specification Group (ISG) on the RIS technology in September 2021. This article provides a comprehensive overview of the status of the work conducted by the ETSI ISG RIS, covering typical deployment scenarios of reconfigurable metasurfaces, use cases and operating applications, requirements, emerging hardware architectures and operating modes, as well as the latest insights regarding future directions of RISs and the resulting smart wireless environments.

eess.SP↗

arXiv2024

Inverse-designed Photonic Computing Core for Parallel Matrix-vector Multiplication

On-chip optical neural networks (ONNs) have recently emerged as an attractive hardware accelerator for deep learning applications, characterized by high computing density, low latency, and compact size. As these networks rely heavily on massive matrix multiplication, photonic computing cores for matrix computation become crucial components for on-chip ONNs, which harness the degree of freedoms (DOFs) in photonics including space, wavelength and mode dimensions. However, previous photonic computing devices have not fully utilized the orthogonality and the conversion characteristic of the waveguide modes, which as we show here, allows for the simultaneous parallel computing of several independent matrix-vector multiplications within the same device. In this work, we propose an inverse-designed photonic computing core for parallel matrix-vector multiplication. The matrices are implemented through a mode conversion process, where the input fundamental modes are simultaneously converted into several orthogonal output modes. Specifically, we target the complex-valued conversion matrices between input and output modes and inversely design the dielectric distribution within the device to achieve parallel matrix-vector multiplication. As a demonstration, the proposed photonic computing core supports simultaneous parallel computing of two independent matrix-vector multiplications, with an ultra-compact footprint and high computing precision (relative error < 8%) at 1550 nm wavelength. The inverse-designed photonic computing devices hold great potential for high-performance on-chip ONNs with low energy consumption and high computing density.

physics.optics↗

arXiv2023

High-throughput optical neural networks based on temporal computing

An emerging generative artificial intelligence (AI) based on neural networks starts to grow in popularity with a revolutionizing capability of creating new and original content. As giant generative models with millions to billions of parameters are developed, trained and maintained, a massive and energy-efficient computing power is highly required. However, conventional digital computers are struggling to keep up with the pace of the generative model improvements. In this paper, we propose and demonstrate high-throughput optical neural networks based on temporal computing. The core weighted summation operation is realized with the use of high-speed electro-optic modulation and low-speed balanced photodetection. The input data and weight are encoded in a time sequence separately and loaded on an optical signal via two electro-optic modulators sequentially. By precisely controlling the synchronization time of the data and weight loading, the matrix multiplication is performed. Followed by a balanced photodetector, the summation is conducted, thanks to the electron accumulation of the inherent electronic integrator circuit of the low-speed photodetector. Thus, the linear weighted summation operation is implemented based on temporal computing in the optical domain. With the proposed optical linear weighted summation, a fully-connected neural network and convolutional neural network are realized. Thanks to the high-speed feature of temporal computing, a high data throughput of the optical neural network is experimentally demonstrated, and the weighting coefficients can be specified on demand, which enables a strong programmability of the optical neural network. By leveraging wavelength multiplexing technology, a scalable optical neural network could be created with a massive computing power and strong reconfigurability, which holds great potential for future giant AI applications.

cs.ET↗

arXiv2023

Joint Beam Scheduling and Power Optimization for Beam Hopping LEO Satellite Systems

Low earth orbit (LEO) satellite communications can provide ubiquitous and reliable services, making it an essential part of the Internet of Everything network. Beam hopping (BH) is an emerging technology for effectively addressing the issue of low resource utilization caused by the non-uniform spatio-temporal distribution of traffic demands. However, how to allocate multi-dimensional resources in a timely and efficient way for the highly dynamic LEO satellite systems remains a challenge. This paper proposes a joint beam scheduling and power optimization beam hopping (JBSPO-BH) algorithm considering the differences in the geographic distribution of sink nodes. The JBSPO-BH algorithm decouples the original problem into two sub-problems. The beam scheduling problem is modelled as a potential game, and the Nash equilibrium (NE) point is obtained as the beam scheduling strategy. Moreover, the penalty function interior point method is applied to optimize the power allocation. Simulation results show that the JBSPO-BH algorithm has low time complexity and fast convergence and achieves better performance both in throughput and fairness. Compared with greedy-based BH, greedy-based BH with the power optimization, round-robin BH, Max-SINR BH and satellite resource allocation algorithm, the throughput of the proposed algorithm is improved by 44.99%, 20.79%, 156.06%, 15.39% and 8.17%, respectively.

cs.NI↗

arXiv2023

Microdisk modulator-assisted optical nonlinear activation functions for photonic neural networks

On-chip implementation of optical nonlinear activation functions (NAFs) is essential for realizing large-scale photonic neural chips. To implement different neural processing and machine learning tasks with optimal performances, different NAFs are explored with the use of different devices. From the perspective of on-chip integration and reconfigurability of photonic neural network (PNN), it is highly preferred that a single compact device can fulfill multiple NAFs. Here, we propose and experimentally demonstrate a compact high-speed microdisk modulator to realize multiple NAFs. The fabricated microdisk modulator has an add-drop configuration in which a lateral PN junction is incorporated for tuning. Based on high-speed nonlinear electrical-optical (E-O) effect, multiple NAFs are realized by electrically controlling free-carrier injection. Thanks to its strong optical confinement of the disk cavity, all-optical thermo-optic (TO) nonlinear effect can also be leveraged to realize other four different NAFs, which is difficult to be realized with the use of electrical-optical effect. With the use of the realized nonlinear activation function, a convolutional neural network (CNN) is studied to perform handwritten digit classification task, and an accuracy as large as 98% is demonstrated, which verifies the effectiveness of the use of the high-speed microdisk modulator to realize the NAFs. Thanks to its compact footprint and strong electrical-optical or all-optical effects, the microdisk modulator features multiple NAFs, which could serve as a flexible nonlinear unit for large-scale PNNs.

physics.optics↗

arXiv2023

Reconfigurable integrated full-dimensional optical lattice generator

Optical lattices with periodic potentials have attracted great attention in modern optics and photonics, enabling extensive applications in atomic manipulation, optical trapping, optical communications, imaging, sensing, etc. In the last decade, the generation of optical lattices has been widely investigated by various approaches such as multi-plane-wave interferometer, beam superposition, spatial light modulators, nanophotonic circuits, etc. However, all of the previous state-of-the-art works are restricted to only one or two dimensions of the light field, which cannot fulfill the increasing demand on complex light manipulation. Full-dimensional and dynamic control of the light field, including spatial amplitude, phase and polarization, is quite challenging and indispensable for the generation of sophisticated optical lattices. Here, we propose and demonstrate a reconfigurable integrated full-dimensional optical lattice generator, i.e. a photonic emitting array (PEA) enabling reconfigurable and full-dimensional manipulation of optical lattices, in which 4x4 photonic emitting units (PEUs) with 64 thermo-optic microheaters are densely integrated on a silicon chip. By engineering each PEU precisely with independent and complete control of optical properties of amplitude, phase and polarization, various optical vortex lattices, cylindrical vector beam lattices, and vector vortex beam lattices can be generated and reconfigured in the far field. The demonstrated integrated optical lattice generator paves the way for the miniaturization, full-dimensional control and enhanced flexibility of complex light manipulation.

physics.optics↗

arXiv2022

Test-time Adaptation with Calibration of Medical Image Classification Nets for Label Distribution Shift

Class distribution plays an important role in learning deep classifiers. When the proportion of each class in the test set differs from the training set, the performance of classification nets usually degrades. Such a label distribution shift problem is common in medical diagnosis since the prevalence of disease vary over location and time. In this paper, we propose the first method to tackle label shift for medical image classification, which effectively adapt the model learned from a single training label distribution to arbitrary unknown test label distribution. Our approach innovates distribution calibration to learn multiple representative classifiers, which are capable of handling different one-dominating-class distributions. When given a test image, the diverse classifiers are dynamically aggregated via the consistency-driven test-time adaptation, to deal with the unknown test label distribution. We validate our method on two important medical image classification tasks including liver fibrosis staging and COVID-19 severity prediction. Our experiments clearly show the decreased model performance under label shift. With our method, model performance significantly improves on all the test datasets with different label shifts for both medical image diagnosis tasks.

eess.IV↗

arXiv2022

Rapid model transfer for medical image segmentation via iterative human-in-the-loop update: from labelled public to unlabelled clinical datasets for multi-organ segmentation in CT

Despite the remarkable success on medical image analysis with deep learning, it is still under exploration regarding how to rapidly transfer AI models from one dataset to another for clinical applications. This paper presents a novel and generic human-in-the-loop scheme for efficiently transferring a segmentation model from a small-scale labelled dataset to a larger-scale unlabelled dataset for multi-organ segmentation in CT. To achieve this, we propose to use an igniter network which can learn from a small-scale labelled dataset and generate coarse annotations to start the process of human-machine interaction. Then, we use a sustainer network for our larger-scale dataset, and iteratively updated it on the new annotated data. Moreover, we propose a flexible labelling strategy for the annotator to reduce the initial annotation workload. The model performance and the time cost of annotation in each subject evaluated on our private dataset are reported and analysed. The results show that our scheme can not only improve the performance by 19.7% on Dice, but also expedite the cost time of manual labelling from 13.87 min to 1.51 min per CT volume during the model transfer, demonstrating the clinical usefulness with promising potentials.

cs.CV↗

arXiv2021

ASAP: A Chinese Review Dataset Towards Aspect Category Sentiment Analysis and Rating Prediction

Sentiment analysis has attracted increasing attention in e-commerce. The sentiment polarities underlying user reviews are of great value for business intelligence. Aspect category sentiment analysis (ACSA) and review rating prediction (RP) are two essential tasks to detect the fine-to-coarse sentiment polarities. %Considering the sentiment of the aspects(ACSA) and the overall review rating(RP) simultaneously has the potential to improve the overall performance. ACSA and RP are highly correlated and usually employed jointly in real-world e-commerce scenarios. While most public datasets are constructed for ACSA and RP separately, which may limit the further exploitation of both tasks. To address the problem and advance related researches, we present a large-scale Chinese restaurant review dataset \textbf{ASAP} including $46,730$ genuine reviews from a leading online-to-offline (O2O) e-commerce platform in China. Besides a $5$-star scale rating, each review is manually annotated according to its sentiment polarities towards $18$ pre-defined aspect categories. We hope the release of the dataset could shed some light on the fields of sentiment analysis. Moreover, we propose an intuitive yet effective joint model for ACSA and RP. Experimental results demonstrate that the joint model outperforms state-of-the-art baselines on both tasks.

cs.CL↗

arXiv2020

The neutron returning time in a linear potential

In this paper, we calculate the quantum time delays for neutron scattering off the Earth's linear gravitational potential. The quantum time delays are obtained by subtracting the classical returning time (CRT) from the Wigner time, the dwell time and the redefined Larmor time respectively. Different from the conventional definition, our Larmor time is defined by aligning the magnetic field along the neutron propagation direction, and this definition does give reasonable results for motions through a free region and a square barrier. It is worth noting that in the zero magnetic field limit, the Larmor time coincides well with the CRT, which is due to the special shape of linear barrier, and may have some relevance to the weak equivalence principle. It is also found that the classical forbidden region plays an essential role for the dwell time $τ_{_\mathrm{DW}}$ to match with the CRT, and the difference between the dwell and the phase times, \ie, the self-interference time delay, is barrier shape sensitive and clearly shows the peculiarity of the linear barrier. All the time delays are on the order of sub-millisecond and exhibit oscillating behaviors, signaling the self-interference of the scattering neutron, and the oscillations become evident only when the de Broglie wavelength $λ_k=2π/k$ is comparable to the characteristic length $L_c=[2m^2g/\hbar^2]^{-1/3}$. If the time delay measurement is experimentally realizable, it can probe the quantum nature for particle scattering off the gravitational potential in the temporal domain.

quant-ph↗

arXiv2020

Smart Contract-based Secure Spectrum Sharing in Multi-Operators Wireless Communication Networks

Multiple-operators (multi-OPs) spectrum sharing mechanism can effectively improve the spectrum utilization in fifth-generation (5G) wireless communication networks. The secondary users are introduced to opportunistically access the licensed spectrum of idle operators (OPs). However, the identity privacy and data security issues raise great concerns about the secure spectrum sharing among multi-OPs. To address these challenges, a consortium blockchain trust framework is proposed for the spectrum sharing in multi-OPs wireless communication networks in this paper. A real consortium blockchain is constructed among multi-OPs. The Multi-Ops Spectrum Sharing (MOSS) smart contract is designed on the constructed consortium blockchain to implement the spectrum trading among multi-OPs. Without the need of trustless spectrum broker, the MOSS smart contract enforces multi-OPs to share the spectrum truthfully and designs a punishment mechanism to punish malicious OPs. Simulation results tested on the Remix integrated development environment (IDE) indicate the feasibility of the designed MOSS smart contract. The performance analysis of the proposed consortium blockchain trust framework demonstrates that the privacy, openness and fairness of the proposed solution are better than traditional spectrum allocation solutions.

cs.NI↗

arXiv2019

Ultra-directional high-efficient chiral silicon photonic circuits

Chiral light matter interaction enables new fundamental researches and applications of light. The interaction has traditionally faced challenges in low directionality and efficiency based on spin orbit interaction of light in microscopic waveguides. It is pivotal to exploit photonic integrated circuits to efficiently engineer photonic chiral behavior. Here, we present ultra directional high efficient chiral coupling in silicon photonic circuits based on low order to high order mode conversion and interference. We show that the directionality of chiral coupling, in principle, can approach minus/plus 1 with circular polarization inputs, benefited from the underlying mechanism of complete destructive and constructive interference. The chiral coupling efficiency can exceed 70%, with negligible scattering to nonguided modes, much higher than conventional coupling mechanisms. Moreover, the chiral silicon photonic circuits can function as a perfect 3 dB power splitter for arbitrarily linear polarization inputs, and also open up the possibility of on chip chirality determination to further flourish the development of chiral optics.

physics.app-ph↗

arXiv2019

Energy Efficiency of Generalized Spatial Modulation Aided Massive MIMO Systems

One of focuses in green communication studies is the energy efficiency (EE) of massive multiple-input multiple-output (MIMO) systems. Although the massive MIMO technology can improve the spectral efficiency (SE) of cellular networks by configuring a large number of antennas at base stations (BSs), the energy consumption of radio frequency (RF) chains increases dramatically. The increment of energy consumption is caused by the increase of RF chain number to match the antenna number in massive MIMO communication systems. To overcome this problem, a generalized spatial modulation (GSM) solution is presented to simultaneously reduce the number of RF chains and maintain the SE of massive MIMO communication systems. A EE model is proposed to estimate the transmission and computation power of massive MIMO communication systems with GSM. Simulation results demonstrate that the EE of massive MIMO communication systems with GSM outperforms the massive MIMO communication systems without GSM. Besides, the computation power consumed by massive MIMO communication systems with GSM is effectively reduced.

cs.NI↗