arXiv subjects

Wenrui Zhang

Publications and source records attributed to Wenrui Zhang.

At least 19 recordsLinked to original sources

arXiv2026

Program-Synthesis-Driven Autodesign of Universal Unitary Operators

We demonstrate that AI-driven program synthesis can autonomously discover fundamental strategies for decomposing unitary matrices in photonic networks. By extending DreamCoder to complex-valued linear algebra, the system generates decomposition programs achieving the minimal $N(N-1)/2$ Mach-Zehnder interferometers, distinct from both Reck and Clements architectures. Learned programs encode dimension-agnostic invariants: strategies discovered for $5 \times 5$ matrices generalize to higher dimensions such as $64 \times 64$. The discovered programs encode interpretable, dimension-agnostic construction rules. These rules generalize across matrix sizes without retraining, demonstrating that autonomous program synthesis can serve as a scalable paradigm for algorithm discovery and the automated design of universal unitary operators. Beyond universal decompositions, the system automatically exploits matrix structure to reduce the interferometer count below the universal theoretical bound. For instance, for Householder matrices, it discovers a dimension-independent rule that requires only $2N-3$ MZIs. This achieves linear, rather than quadratic, scaling and generalizes to arbitrary $N$ without retraining. For matrices obtained from the singular value decomposition of sparse matrices, reductions generally increase with sparsity, reaching up to 38% fewer MZIs than the universal theoretical bound $N(N-1)/2$ at 95% sparsity. These MZI reductions translate directly into practical hardware benefits for scalable photonic implementations. Taken together, the system functions as a single unified engine that discovers both universal decomposition rules and matrix-specific optimizations, without being provided with the structural or analytical properties of the input matrices.

physics.optics↗

arXiv2026

Wafer-scale Demonstration of High-voltage beta-Ga2O3 MOSFETs with Excellent Uniformity and over 3kV Breakdown Voltages

This study demonstrates a wafer-scale growth of a 2-inch Si-doped $β$-Ga2O3 (100) epitaxial wafer and the realization of uniform, high-voltage lateral $β$-Ga2O3 MOSFET arrays. The 2-inch homoepitaxial $β$-Ga2O3 (100) film grown by MOCVD exhibit excellent crystalline uniformity with an average rocking curve FWHM of ~27.0 arcsec and a low surface roughness less than 1 nm, alongside a uniform net doping concentration on the value of 4.60 $\times$ 1E17 cm-3. The fabricated MOSFETs deliver a threshold voltage of -31.75 V, a drain-current on/off ratio over 1E9, a specific on-resistance of 126.52 mohm$\cdot$cm2 and breakdown voltage exceeding 3 kV. Statistical analysis across the entire wafer presents good device uniformity, with threshold voltages ranging from -28 V to -36 V, output current densities of 60-75 mA/mm, and a breakdown voltage over 3 kV. These results provide the demonstration using the 2-inch $β$-Ga2O3 epitaxial wafer to realize high-voltage $β$-Ga2O3 MOSFETs with wafer-scale performance uniformity for next-generation power device application.

cond-mat.mtrl-sci↗

arXiv2026

One-Dimensional Metallic Polymeric Nitrogen

The pressure-induced metallic states of light elements attract significant attention, because of potential applications as high-temperature superconductor and high-energy-density material, especially for hydrogen and nitrogen1-10. Several semiconducting polymeric nitrogen phases with three- or two-dimensional sp3-bonded networks were synthesized6-10, but its metallic form remains unobserved. Here, we report the synthesis of a metallic polymeric nitrogen with one-dimensional feature (1D-PN) at 130-140 GPa and above 3000 K. Synchrotron XRD and Raman spectroscopy, supported by DFT calculations, reveal that it adopts an infinite arm-chair like chain with sp2-hybridized pi-bonds. Simulations predict a superconducting transition at 21.19 K under 113 GPa, higher than that reported in high-pressure experiments for non-metallic elements. At ambient pressure, this phase acquiring an energy density of as high as 8.78 kJ/g is not only kinetically stable but also thermodynamically more stable than cubic gauche nitrogen. This multifunctional property profile positions 1D-PN as a disruptive candidate for both electronic and energetic applications.

cond-mat.mtrl-sci↗

arXiv2026

EvoC2Rust: A Skeleton-guided Framework for Project-Level C-to-Rust Translation

Translating legacy C codebases to Rust is increasingly demanded for building safety-critical systems. While various approaches have emerged for this task, they face inherent trade-offs: rule-based methods often struggle to satisfy code safety and idiomaticity requirements, while LLM-based methods frequently fail to generate semantically equivalent Rust code, due to the heavy dependencies of modules across the entire codebase. Recent studies have revealed that both solutions are limited to small-scale programs. In this paper, we propose EvoC2Rust, an automated framework for converting complete C projects to equivalent Rust ones. EvoC2Rust employs a skeleton-guided translation strategy for project-level translation. The pipeline consists of three stages: 1) it first decomposes the C project into functional modules, employs a feature-mapping-enhanced LLM to transform definitions and macros, and generates type-checked function stubs, which form a compilable Rust skeleton; 2) it then incrementally translates functions, replacing the corresponding stub placeholders; 3) finally, it repairs compilation errors by integrating LLM and static analysis. Through evolutionary augmentation, EvoC2Rust combines the advantages of both rule-based and LLM-based solutions. Our evaluation on open-source benchmarks and six industrial projects demonstrates the superior performance of EvoC2Rust in project-level C-to-Rust translation. The results show that our approach outperforms the strongest LLM-based baseline by 17.24% in syntax accuracy and 14.32% in semantic accuracy, while also achieving a 43.59% higher code safety rate than the best rule-based tool.

cs.SE↗

arXiv2025

MolSight: Optical Chemical Structure Recognition with SMILES Pretraining, Multi-Granularity Learning and Reinforcement Learning

Optical Chemical Structure Recognition (OCSR) plays a pivotal role in modern chemical informatics, enabling the automated conversion of chemical structure images from scientific literature, patents, and educational materials into machine-readable molecular representations. This capability is essential for large-scale chemical data mining, drug discovery pipelines, and Large Language Model (LLM) applications in related domains. However, existing OCSR systems face significant challenges in accurately recognizing stereochemical information due to the subtle visual cues that distinguish stereoisomers, such as wedge and dash bonds, ring conformations, and spatial arrangements. To address these challenges, we propose MolSight, a comprehensive learning framework for OCSR that employs a three-stage training paradigm. In the first stage, we conduct pre-training on large-scale but noisy datasets to endow the model with fundamental perception capabilities for chemical structure images. In the second stage, we perform multi-granularity fine-tuning using datasets with richer supervisory signals, systematically exploring how auxiliary tasks-specifically chemical bond classification and atom localization-contribute to molecular formula recognition. Finally, we employ reinforcement learning for post-training optimization and introduce a novel stereochemical structure dataset. Remarkably, we find that even with MolSight's relatively compact parameter size, the Group Relative Policy Optimization (GRPO) algorithm can further enhance the model's performance on stereomolecular. Through extensive experiments across diverse datasets, our results demonstrate that MolSight achieves state-of-the-art performance in (stereo)chemical optical structure recognition.

cs.CV↗

arXiv2024

Efficient Circuit Cutting and Scheduling in a Multi-Node Quantum System with Dynamic EPR Pairs

Despite advancements, current quantum hardware faces significant challenges, including limited qubit counts and high susceptibility to noise, which hinder the execution of large, complex algorithms. To address these limitations, multi-node quantum systems and quantum circuit cutting techniques partition large circuits into smaller subcircuits that can be executed on individual quantum machines and then reconstructed using classical resources. However, these methods introduce new challenges, such as the large overhead from subcircuit reconstruction and additional noise from entangled EPR pairs, especially in multi-node quantum systems. In this paper, we propose the Efficient Circuit Cutting and Scheduling (EC2S) system, which integrates EPR pairs with circuit cutting to address these issues. EC2S improves system performance by transitioning from logical to physical EPR pairs and further reduces computational overhead by minimizing the number of subcircuits during the reconstruction phase. \sol~ is implemented using Qiskit and evaluated on both real quantum hardware and various emulators. Compared to the state-of-the-art Qiskit-Addon-Cut, EC2S achieves significant improvements in fidelity, up to 16.7\%, and reduces system-wide expenditure by up to 99.5\%.

cs.DC↗

arXiv2024

A Lightweight Framework for Adaptive Retrieval In Code Completion With Critique Model

Recent advancements in Retrieval-Augmented Generation have significantly enhanced code completion at the repository level. Various RAG-based code completion systems are proposed based on different design choices. For instance, gaining more effectiveness at the cost of repeating the retrieval-generation process multiple times. However, the indiscriminate use of retrieval in current methods reveals issues in both efficiency and effectiveness, as a considerable portion of retrievals are unnecessary and may introduce unhelpful or even harmful suggestions to code language models. To address these challenges, we introduce CARD, a lightweight critique method designed to provide insights into the necessity of retrievals and select the optimal answer from multiple predictions. CARD can seamlessly integrate into any RAG-based code completion system. Our evaluation shows that CARD saves 21% to 46% times of retrieval for Line completion, 14% to 40% times of retrieval for API completion, and 6% to 46.5% times of retrieval for function completion respectively, while improving the accuracy. CARD reduces latency ranging from 16% to 83%. CARD is generalizable to different LMs, retrievers, and programming languages. It is lightweight with training in few seconds and inference in few milliseconds.

cs.SE↗

arXiv2023

Composing Recurrent Spiking Neural Networks using Locally-Recurrent Motifs and Risk-Mitigating Architectural Optimization

In neural circuits, recurrent connectivity plays a crucial role in network function and stability. However, existing recurrent spiking neural networks (RSNNs) are often constructed by random connections without optimization. While RSNNs can produce rich dynamics that are critical for memory formation and learning, systemic architectural optimization of RSNNs is still an open challenge. We aim to enable systematic design of large RSNNs via a new scalable RSNN architecture and automated architectural optimization. We compose RSNNs based on a layer architecture called Sparsely-Connected Recurrent Motif Layer (SC-ML) that consists of multiple small recurrent motifs wired together by sparse lateral connections. The small size of the motifs and sparse inter-motif connectivity leads to an RSNN architecture scalable to large network sizes. We further propose a method called Hybrid Risk-Mitigating Architectural Search (HRMAS) to systematically optimize the topology of the proposed recurrent motifs and SC-ML layer architecture. HRMAS is an alternating two-step optimization process by which we mitigate the risk of network instability and performance degradation caused by architectural change by introducing a novel biologically-inspired "self-repairing" mechanism through intrinsic plasticity. The intrinsic plasticity is introduced to the second step of each HRMAS iteration and acts as unsupervised fast self-adaptation to structural and synaptic weight modifications introduced by the first step during the RSNN architectural "evolution". To the best of the authors' knowledge, this is the first work that performs systematic architectural optimization of RSNNs. Using one speech and three neuromorphic datasets, we demonstrate the significant performance improvement brought by the proposed automated architecture optimization over existing manually-designed RSNNs.

cs.NE↗

arXiv2023

Self-Supervised Time Series Representation Learning via Cross Reconstruction Transformer

Unsupervised/self-supervised representation learning in time series is critical since labeled samples are usually scarce in real-world scenarios. Existing approaches mainly leverage the contrastive learning framework, which automatically learns to understand the similar and dissimilar data pairs. Nevertheless, they are restricted to the prior knowledge of constructing pairs, cumbersome sampling policy, and unstable performances when encountering sampling bias. Also, few works have focused on effectively modeling across temporal-spectral relations to extend the capacity of representations. In this paper, we aim at learning representations for time series from a new perspective and propose Cross Reconstruction Transformer (CRT) to solve the aforementioned problems in a unified way. CRT achieves time series representation learning through a cross-domain dropping-reconstruction task. Specifically, we transform time series into the frequency domain and randomly drop certain parts in both time and frequency domains. Dropping can maximally preserve the global context compared to cropping and masking. Then a transformer architecture is utilized to adequately capture the cross-domain correlations between temporal and spectral information through reconstructing data in both domains, which is called Dropped Temporal-Spectral Modeling. To discriminate the representations in global latent space, we propose Instance Discrimination Constraint to reduce the mutual information between different time series and sharpen the decision boundaries. Additionally, we propose a specified curriculum learning strategy to optimize the CRT, which progressively increases the dropping ratio in the training process.

cs.LG↗

arXiv2023

Directional carrier transport in micrometer-thick gallium oxide films for high-performance deep-ultraviolet photodetection

Incorporating emerging ultrawide bandgap semiconductors with a metal-semiconductor-metal (MSM) architecture is highly desired for deep-ultraviolet (DUV) photodetection. However, synthesis-induced defects in semiconductors complicate the rational design of MSM DUV photodetectors due to their dual role as carrier donors and trap centers, leading to a commonly observed trade-off between responsivity and response time. Here, we demonstrate a simultaneous improvement of these two parameters in ε-Ga2O3 MSM photodetectors by establishing a low-defect diffusion barrier for directional carrier transport. Specifically, using a micrometer thickness far exceeding its effective light absorption depth, the ε-Ga2O3 MSM photodetector achieves over 18-fold enhancement of responsivity and simultaneous reduction of the response time, which exhibits a state-of-the-art photo-to-dark current ratio near 10^8, a superior responsivity of >1300 A/W, an ultrahigh detectivity of >10^16 Jones and a decay time of 123 ms. Combined depth-profile spectroscopic and microscopic analysis reveals the existence of a broad defective region near the lattice-mismatched interface followed by a more defect-free dark region, while the latter one serves as a diffusion barrier to assist frontward carrier transport for substantially enhancing the photodetector performance. This work reveals the critical role of the semiconductor defect profile in tuning carrier transport for fabricating high-performance MSM DUV photodetectors.

cond-mat.mtrl-sci↗

arXiv2022

A Simple Self-Supervised ECG Representation Learning Method via Manipulated Temporal-Spatial Reverse Detection

Learning representations from electrocardiogram (ECG) signals can serve as a fundamental step for different machine learning-based ECG tasks. In order to extract general ECG representations that can be adapted to various downstream tasks, the learning process needs to be based on a general ECG-related task which can be achieved through self-supervised learning (SSL). However, existing SSL approaches either fail to provide satisfactory ECG representations or require too much effort to construct the learning data. In this paper, we propose the T-S reverse detection, a simple yet effective self-supervised approach to learn ECG representations. Inspired by the temporal and spatial characteristics of ECG signals, we flip the original signals horizontally (temporal reverse), vertically (spatial reverse), and both horizontally and vertically (temporal-spatial reverse). Learning is then done by classifying four types of signals including the original one. To verify the effectiveness of the proposed method, we perform a downstream task to detect atrial fibrillation (AF) which is one of the most common ECG tasks. The results show that the ECG representations learned with our method achieve remarkable performance. Furthermore, after exploring the representation feature space and investigating salient ECG locations, we conclude that the temporal reverse is more effective for learning ECG representations than the spatial reverse.

cs.LG↗

arXiv2022

MetaVA: Curriculum Meta-learning and Pre-fine-tuning of Deep Neural Networks for Detecting Ventricular Arrhythmias based on ECGs

Ventricular arrhythmias (VA) are the main causes of sudden cardiac death. Developing machine learning methods for detecting VA based on electrocardiograms (ECGs) can help save people's lives. However, developing such machine learning models for ECGs is challenging because of the following: 1) group-level diversity from different subjects and 2) individual-level diversity from different moments of a single subject. In this study, we aim to solve these problems in the pre-training and fine-tuning stages. For the pre-training stage, we propose a novel model agnostic meta-learning (MAML) with curriculum learning (CL) method to solve group-level diversity. MAML is expected to better transfer the knowledge from a large dataset and use only a few recordings to quickly adapt the model to a new person. CL is supposed to further improve MAML by meta-learning from easy to difficult tasks. For the fine-tuning stage, we propose improved pre-fine-tuning to solve individual-level diversity. We conduct experiments using a combination of three publicly available ECG datasets. The results show that our method outperforms the compared methods in terms of all evaluation metrics. Ablation studies show that MAML and CL could help perform more evenly, and pre-fine-tuning could better fit the model to training data.

cs.LG↗

arXiv2022

A Deep Bayesian Neural Network for Cardiac Arrhythmia Classification with Rejection from ECG Recordings

With the development of deep learning-based methods, automated classification of electrocardiograms (ECGs) has recently gained much attention. Although the effectiveness of deep neural networks has been encouraging, the lack of information given by the outputs restricts clinicians' reexamination. If the uncertainty estimation comes along with the classification results, cardiologists can pay more attention to "uncertain" cases. Our study aims to classify ECGs with rejection based on data uncertainty and model uncertainty. We perform experiments on a real-world 12-lead ECG dataset. First, we estimate uncertainties using the Monte Carlo dropout for each classification prediction, based on our Bayesian neural network. Then, we accept predictions with uncertainty under a given threshold and provide "uncertain" cases for clinicians. Furthermore, we perform a simulation experiment using varying thresholds. Finally, with the help of a clinician, we conduct case studies to explain the results of large uncertainties and incorrect predictions with small uncertainties. The results show that correct predictions are more likely to have smaller uncertainties, and the performance on accepted predictions improves as the accepting ratio decreases (i.e. more rejections). Case studies also help explain why rejection can improve the performance. Our study helps neural networks produce more accurate results and provide information on uncertainties to better assist clinicians in the diagnosis process. It can also enable deep-learning-based ECG interpretation in clinical implementation.

eess.SP↗

arXiv2021

Backpropagated Neighborhood Aggregation for Accurate Training of Spiking Neural Networks

While backpropagation (BP) has been applied to spiking neural networks (SNNs) achieving encouraging results, a key challenge involved is to backpropagate a continuous-valued loss over layers of spiking neurons exhibiting discontinuous all-or-none firing activities. Existing methods deal with this difficulty by introducing compromises that come with their own limitations, leading to potential performance degradation. We propose a novel BP-like method, called neighborhood aggregation (NA), which computes accurate error gradients guiding weight updates that may lead to discontinuous modifications of firing activities. NA achieves this goal by aggregating finite differences of the loss over multiple perturbed membrane potential waveforms in the neighborhood of the present membrane potential of each neuron while utilizing a new membrane potential distance function. Our experiments show that the proposed NA algorithm delivers the state-of-the-art performance for SNN training on several datasets.

cs.NE↗

arXiv2021

Temporal Spike Sequence Learning via Backpropagation for Deep Spiking Neural Networks

Spiking neural networks (SNNs) are well suited for spatio-temporal learning and implementations on energy-efficient event-driven neuromorphic processors. However, existing SNN error backpropagation (BP) methods lack proper handling of spiking discontinuities and suffer from low performance compared with the BP methods for traditional artificial neural networks. In addition, a large number of time steps are typically required to achieve decent performance, leading to high latency and rendering spike-based computation unscalable to deep architectures. We present a novel Temporal Spike Sequence Learning Backpropagation (TSSL-BP) method for training deep SNNs, which breaks down error backpropagation across two types of inter-neuron and intra-neuron dependencies and leads to improved temporal learning precision. It captures inter-neuron dependencies through presynaptic firing times by considering the all-or-none characteristics of firing activities and captures intra-neuron dependencies by handling the internal evolution of each neuronal state in time. TSSL-BP efficiently trains deep SNNs within a much shortened temporal window of a few steps while improving the accuracy for various image classification datasets including CIFAR10.

cs.NE↗

arXiv2021

Robust Deep Multi-Modal Sensor Fusion using Fusion Weight Regularization and Target Learning

Sensor fusion has wide applications in many domains including health care and autonomous systems. While the advent of deep learning has enabled promising multi-modal fusion of high-level features and end-to-end sensor fusion solutions, existing deep learning based sensor fusion techniques including deep gating architectures are not always resilient, leading to the issue of fusion weight inconsistency. We propose deep multi-modal sensor fusion architectures with enhanced robustness particularly under the presence of sensor failures. At the core of our gating architectures are fusion weight regularization and fusion target learning operating on auxiliary unimodal sensing networks appended to the main fusion model. The proposed regularized gating architectures outperform the existing deep learning architectures with and without gating under both clean and corrupted sensory inputs resulted from sensor failures. The demonstrated improvements are particularly pronounced when one or more multiple sensory modalities are corrupted.

cs.LG↗

arXiv2020

Deep Bayesian Local Crystallography

The advent of high-resolution electron and scanning probe microscopy imaging has opened the floodgates for acquiring atomically resolved images of bulk materials, 2D materials, and surfaces. This plethora of data contains an immense volume of information on materials structures, structural distortions, and physical functionalities. Harnessing this knowledge regarding local physical phenomena necessitates the development of the mathematical frameworks for extraction of relevant information. However, the analysis of atomically resolved images is often based on the adaptation of concepts from macroscopic physics, notably translational and point group symmetries and symmetry lowering phenomena. Here, we explore the bottom-up definition of structural units and symmetry in atomically resolved data using a Bayesian framework. We demonstrate the need for a Bayesian definition of symmetry using a simple toy model and demonstrate how this definition can be extended to the experimental data using deep learning networks in a Bayesian setting, namely rotationally invariant variational autoencoders.

physics.comp-ph↗

arXiv2020

Skip-Connected Self-Recurrent Spiking Neural Networks with Joint Intrinsic Parameter and Synaptic Weight Training

As an important class of spiking neural networks (SNNs), recurrent spiking neural networks (RSNNs) possess great computational power and have been widely used for processing sequential data like audio and text. However, most RSNNs suffer from two problems. 1. Due to a lack of architectural guidance, random recurrent connectivity is often adopted, which does not guarantee good performance. 2. Training of RSNNs is in general challenging, bottlenecking achievable model accuracy. To address these problems, we propose a new type of RSNNs called Skip-Connected Self-Recurrent SNNs (ScSr-SNNs). Recurrence in ScSr-SNNs is introduced in a stereotyped manner by adding self-recurrent connections to spiking neurons, which implements local memory. The network dynamics is enriched by skip connections between nonadjacent layers. Constructed by simplified self-recurrent and skip connections, ScSr-SNNs are able to realize recurrent behaviors similar to those of more complex RSNNs while the error gradients can be more straightforwardly calculated due to the mostly feedforward nature of the network. Moreover, we propose a new backpropagation (BP) method called backpropagated intrinsic plasticity (BIP) to further boost the performance of ScSr-SNNs by training intrinsic model parameters. Unlike standard intrinsic plasticity rules that adjust the neuron's intrinsic parameters according to neuronal activity, the proposed BIP methods optimize intrinsic parameters based on the backpropagated error gradient of a well-defined global loss function in addition to synaptic weight training. Based upon challenging speech and neuromorphic speech datasets including TI46-Alpha, TI46-Digits, and N-TIDIGITS, the proposed ScSr-SNNs can boost performance by up to 2.55% compared with other types of RSNNs trained by state-of-the-art BP methods.

cs.NE↗