Researcher profile

Mingzhe Liu

Mingzhe Liu contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate

Computer Vision physics.space-ph Artificial Intelligence astro-ph.SR Cryptography and Security Machine Learning physics.plasm-ph

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author

6works

0followers

7topics

4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

BZPEER is loading the nearby papers, people, topics and institutions for this page.

preprint2026arXiv

DCVD: Dual-Channel Cross-Modal Fusion for Joint Vulnerability Detection and Localization

Software vulnerability detection plays a critical role in ensuring system security, where real-world auditing requires not only determining whether a function is vulnerable but also pinpointing the specific lines responsible. However, existing approaches either rely on a single information source -- sequential, structural, or semantic -- failing to jointly exploit the complementary strengths across modalities, or treat statement-level localization merely as a byproduct of function-level detection without explicit line-level supervision. To address these limitations, we propose DCVD (Dual-Channel Cross-Modal Vulnerability Detection), a unified framework that performs joint function-level detection and statement-level localization. DCVD extracts control-dependency and semantic features through two parallel branches and integrates them via contrastive alignment coupled with bidirectional cross-attention, effectively bridging the cross-modal representation gap. It further introduces explicit supervision signals at both the function and statement levels, enabling collaborative optimization across the two granularities. Extensive experiments on a large-scale real-world vulnerability benchmark demonstrate that DCVD consistently outperforms state-of-the-art methods on both function-level detection and statement-level localization. Our code is available at https://github.com/vinsontang1/DCVD.

preprint2025arXiv

U-Net-Like Spiking Neural Networks for Single Image Dehazing

Image dehazing is a critical challenge in computer vision, essential for enhancing image clarity in hazy conditions. Traditional methods often rely on atmospheric scattering models, while recent deep learning techniques, specifically Convolutional Neural Networks (CNNs) and Transformers, have improved performance by effectively analyzing image features. However, CNNs struggle with long-range dependencies, and Transformers demand significant computational resources. To address these limitations, we propose DehazeSNN, an innovative architecture that integrates a U-Net-like design with Spiking Neural Networks (SNNs). DehazeSNN captures multi-scale image features while efficiently managing local and long-range dependencies. The introduction of the Orthogonal Leaky-Integrate-and-Fire Block (OLIFBlock) enhances cross-channel communication, resulting in superior dehazing performance with reduced computational burden. Our extensive experiments show that DehazeSNN is highly competitive to state-of-the-art methods on benchmark datasets, delivering high-quality haze-free images with a smaller model size and less multiply-accumulate operations. The proposed dehazing method is publicly available at https://github.com/HaoranLiu507/DehazeSNN.

preprint2024arXiv

Random-coupled Neural Network

Improving the efficiency of current neural networks and modeling them in biological neural systems have become popular research directions in recent years. Pulse-coupled neural network (PCNN) is a well applicated model for imitating the computation characteristics of the human brain in computer vision and neural network fields. However, differences between the PCNN and biological neural systems remain: limited neural connection, high computational cost, and lack of stochastic property. In this study, random-coupled neural network (RCNN) is proposed. It overcomes these difficulties in PCNN's neuromorphic computing via a random inactivation process. This process randomly closes some neural connections in the RCNN model, realized by the random inactivation weight matrix of link input. This releases the computational burden of PCNN, making it affordable to achieve vast neural connections. Furthermore, the image and video processing mechanisms of RCNN are researched. It encodes constant stimuli as periodic spike trains and periodic stimuli as chaotic spike trains, the same as biological neural information encoding characteristics. Finally, the RCNN is applicated to image segmentation, fusion, and pulse shape discrimination subtasks. It is demonstrated to be robust, efficient, and highly anti-noised, with outstanding performance in all applications mentioned above.

preprint2021arXiv

Analysis of Magnetohydrodynamic Perturbations in Radial-field Solar Wind from Parker Solar Probe Observations

We report analysis of sub-Alfvénic magnetohydrodynamic (MHD) perturbations in the low-\b{eta} radial-field solar wind using the Parker Solar Probe spacecraft data from 31 October to 12 November 2018. We calculate wave vectors using the singular value decomposition method and separate the MHD perturbations into three types of linear eigenmodes (Alfvén, fast, and slow modes) to explore the properties of the sub-Alfvénic perturbations and the role of compressible perturbations in solar wind heating. The MHD perturbations there show a high degree of Alfvénicity in the radial-field solar wind, with the energy fraction of Alfvén modes dominating (~45%-83%) over those of fast modes (~16%-43%) and slow modes (~1%-19%). We present a detailed analysis of a representative event on 10 November 2018. Observations show that fast modes dominate magnetic compressibility, whereas slow modes dominate density compressibility. The energy damping rate of compressible modes is comparable to the heating rate, suggesting the collisionless damping of compressible modes could be significant for solar wind heating. These results are valuable for further studies of the imbalanced turbulence near the Sun and possible heating effects of compressible modes at MHD scales in low-\b{eta} plasma.

preprint2020arXiv

Lifelong Property Price Prediction: A Case Study for the Toronto Real Estate Market

We present Luce, the first life-long predictive model for automated property valuation. Luce addresses two critical issues of property valuation: the lack of recent sold prices and the sparsity of house data. It is designed to operate on a limited volume of recent house transaction data. As a departure from prior work, Luce organizes the house data in a heterogeneous information network (HIN) where graph nodes are house entities and attributes that are important for house price valuation. We employ a Graph Convolutional Network (GCN) to extract the spatial information from the HIN for house-related data like geographical locations, and then use a Long Short Term Memory (LSTM) network to model the temporal dependencies for house transaction data over time. Unlike prior work, Luce can make effective use of the limited house transactions data in the past few months to update valuation information for all house entities within the HIN. By providing a complete and up-to-date house valuation dataset, Luce thus massively simplifies the downstream valuation task for the targeting properties. We demonstrate the benefit of Luce by applying it to large, real-life datasets obtained from the Toronto real estate market. Extensive experimental results show that Luce not only significantly outperforms prior property valuation methods but also often reaches and sometimes exceeds the valuation accuracy given by independent experts when using the actual realization price as the ground truth.

preprint2020arXiv

PIC simulations of microinstabilities and waves at near-Sun solar wind perpendicular shocks: Predictions for Parker Solar Probe and Solar Orbiter

Microinstabilities and waves excited at moderate-Mach-number perpendicular shocks in the near-Sun solar wind are investigated by full particle-in-cell (PIC) simulations. By analyzing the dispersion relation of fluctuating field components directly issued from the shock simulation, we obtain key findings concerning wave excitations at the shock front: (1) at the leading edge of the foot, two types of electrostatic (ES) waves are observed. The relative drift of the reflected ions versus the electrons triggers an electron cyclotron drift instability (ECDI) which excites the first ES wave. Because the bulk velocity of gyro-reflected ions shifts to the direction of the shock front, the resulting ES wave propagates oblique to the shock normal. Immediately, a fraction of incident electrons are accelerated by this ES wave and a ring-like velocity distribution is generated. They can couple with the hot Maxwellian core and excite the second ES wave around the upper hybrid frequency. (2) from the middle of the foot all the way to the ramp, electrons can couple with both incident and reflected ions. ES waves excited by ECDI in different directions propagate across each other. Electromagnetic (EM) waves (X mode) emitted toward upstream are observed in both regions. They are probably induced by a small fraction of relativistic electrons. Results shed new insight on the mechanism for the occurrence of ES wave excitations and possible EM wave emissions at young CME-driven shocks in the near-Sun solar wind.

Institution

Affiliation not imported yet

This author record came from a source that does not expose affiliation metadata. Once the author claims the profile or we enrich the record from another provider, this section will link to the concrete institution.

Topic footprint