arXiv subjects

Siyun Wang

Publications and source records attributed to Siyun Wang.

7 recordsLinked to original sources

arXiv2025

Ultrahigh Charge-to-Spin Conversion and Tunneling Magnetoresistance in Quasi-Two-Dimensional d-wave Altermagnet

The emergence of altermagnets has driven groundbreaking advances in spintronics. Notably, d-wave altermagnets support non-relativistic spin transport, efficient charge-to-spin conversion, and T-odd spin currents. In addition, their integration as electrodes in antiferromagnetic tunnel junctions (AFMTJs) enables a tunneling magnetoresistance (TMR) effect, allowing electrical detection of Néel vectors for next-generation memory devices. In this work, we investigate the non-relativistic spin transport properties of the quasi-two-dimensional (quasi-2D) d-wave altermagnet KV\textsubscript{2}Se\textsubscript{2}O and the TMR effect in KV\textsubscript{2}Se\textsubscript{2}O-based AFMTJs via first-principles calculations. Our results reveal that KV\textsubscript{2}Se\textsubscript{2}O exhibits a non-relativistic longitudinal spin polarization and a spin Hall angle both exceeding 60\% at room temperature, while KV\textsubscript{2}Se\textsubscript{2}O-based AFMTJs achieve a giant TMR reaching approximately $10^{12}$\%, which remains robust against Fermi level shifts. These findings highlight the anisotropic spin polarization inherent to d-wave staggered magnetism and underscore the critical role of Fermi surface topology in enhancing T-odd spin transport and the TMR effect in AFMTJs.

cond-mat.mtrl-sci↗

arXiv2025

SuiGPT MAD: Move AI Decompiler to Improve Transparency and Auditability on Non-Open-Source Blockchain Smart Contract

The vision of Web3 is to improve user control over data and assets, but one challenge that complicates this vision is the prevalence of non-transparent, scam-prone applications and vulnerable smart contracts that put Web3 users at risk. While code audits are one solution to this problem, the lack of smart contracts source code on many blockchain platforms, such as Sui, hinders the ease of auditing. A promising approach to this issue is the use of a decompiler to reverse-engineer smart contract bytecode. However, existing decompilers for Sui produce code that is difficult to understand and cannot be directly recompiled. To address this, we developed the SuiGPT Move AI Decompiler (MAD), a Large Language Model (LLM)-powered web application that decompiles smart contract bytecodes on Sui into logically correct, human-readable, and re-compilable source code with prompt engineering. Our evaluation shows that MAD's output successfully passes original unit tests and achieves a 73.33% recompilation success rate on real-world smart contracts. Additionally, newer models tend to deliver improved performance, suggesting that MAD's approach will become increasingly effective as LLMs continue to advance. In a user study involving 12 developers, we found that MAD significantly reduced the auditing workload compared to using traditional decompilers. Participants found MAD's outputs comparable to the original source code, improving accessibility for understanding and auditing non-open-source smart contracts. Through qualitative interviews with these developers and Web3 projects, we further discussed the strengths and concerns of MAD. MAD has practical implications for blockchain smart contract transparency, auditing, and education. It empowers users to easily and independently review and audit non-open-source smart contracts, fostering accountability and decentralization

cs.HC↗

arXiv2024

Graph Neural Machine: A New Model for Learning with Tabular Data

In recent years, there has been a growing interest in mapping data from different domains to graph structures. Among others, neural network models such as the multi-layer perceptron (MLP) can be modeled as graphs. In fact, MLPs can be represented as directed acyclic graphs. Graph neural networks (GNNs) have recently become the standard tool for performing machine learning tasks on graphs. In this work, we show that an MLP is equivalent to an asynchronous message passing GNN model which operates on the MLP's graph representation. We then propose a new machine learning model for tabular data, the so-called Graph Neural Machine (GNM), which replaces the MLP's directed acyclic graph with a nearly complete graph and which employs a synchronous message passing scheme. We show that a single GNM model can simulate multiple MLP models. We evaluate the proposed model in several classification and regression datasets. In most cases, the GNM model outperforms the MLP architecture.

stat.ML↗

arXiv2022

Decoupled Pyramid Correlation Network for Liver Tumor Segmentation from CT images

Purpose: Automated liver tumor segmentation from Computed Tomography (CT) images is a necessary prerequisite in the interventions of hepatic abnormalities and surgery planning. However, accurate liver tumor segmentation remains challenging due to the large variability of tumor sizes and inhomogeneous texture. Recent advances based on Fully Convolutional Network (FCN) for medical image segmentation drew on the success of learning discriminative pyramid features. In this paper, we propose a Decoupled Pyramid Correlation Network (DPC-Net) that exploits attention mechanisms to fully leverage both low- and high-level features embedded in FCN to segment liver tumor. Methods: We first design a powerful Pyramid Feature Encoder (PFE) to extract multi-level features from input images. Then we decouple the characteristics of features concerning spatial dimension (i.e., height, width, depth) and semantic dimension (i.e., channel). On top of that, we present two types of attention modules, Spatial Correlation (SpaCor) and Semantic Correlation (SemCor) modules, to recursively measure the correlation of multi-level features. The former selectively emphasizes global semantic information in low-level features with the guidance of high-level ones. The latter adaptively enhance spatial details in high-level features with the guidance of low-level ones. Results: We evaluate the DPC-Net on MICCAI 2017 LiTS Liver Tumor Segmentation (LiTS) challenge dataset. Dice Similarity Coefficient (DSC) and Average Symmetric Surface Distance (ASSD) are employed for evaluation. The proposed method obtains a DSC of 76.4% and an ASSD of 0.838 mm for liver tumor segmentation, outperforming the state-of-the-art methods. It also achieves a competitive results with a DSC of 96.0% and an ASSD of 1.636 mm for liver segmentation.

cs.CV↗

arXiv2022

COSPLAY: Concept Set Guided Personalized Dialogue Generation Across Both Party Personas

Maintaining a consistent persona is essential for building a human-like conversational model. However, the lack of attention to the partner makes the model more egocentric: they tend to show their persona by all means such as twisting the topic stiffly, pulling the conversation to their own interests regardless, and rambling their persona with little curiosity to the partner. In this work, we propose COSPLAY(COncept Set guided PersonaLized dialogue generation Across both partY personas) that considers both parties as a "team": expressing self-persona while keeping curiosity toward the partner, leading responses around mutual personas, and finding the common ground. Specifically, we first represent self-persona, partner persona and mutual dialogue all in the concept sets. Then, we propose the Concept Set framework with a suite of knowledge-enhanced operations to process them such as set algebras, set expansion, and set distance. Based on these operations as medium, we train the model by utilizing 1) concepts of both party personas, 2) concept relationship between them, and 3) their relationship to the future dialogue. Extensive experiments on a large public dataset, Persona-Chat, demonstrate that our model outperforms state-of-the-art baselines for generating less egocentric, more human-like, and higher quality responses in both automatic and human evaluations.

cs.CL↗

arXiv2022

A flexible smoother adapted to censored data with outliers and its application to SARS-CoV-2 monitoring in wastewater

A sentinel network, Obépine, has been designed to monitor SARS-CoV-2 viral load in wastewaters arriving at wastewater treatment plants (WWTPs) in France as an indirect macro-epidemiological parameter. The sources of uncertainty in such monitoring system are numerous and the concentration measurements it provides are left-censored and contain outliers, which biases the results of usual smoothing methods. Hence the need for an adapted pre-processing in order to evaluate the real daily amount of virus arriving to each WWTP. We propose a method based on an auto-regressive model adapted to censored data with outliers. Inference and prediction are produced via a discretised smoother which makes it a very flexible tool. This method is both validated on simulations and on real data from Obépine. The resulting smoothed signal shows a good correlation with other epidemiological indicators and is currently used by Obépine to provide an estimate of virus circulation over the watersheds corresponding to about 200 WWTPs.

stat.AP↗

arXiv2018

Identifying Mild Traumatic Brain Injury Patients From MR Images Using Bag of Visual Words

Mild traumatic brain injury (mTBI) is a growing public health problem with an estimated incidence of one million people annually in US. Neurocognitive tests are used to both assess the patient condition and to monitor the patient progress. This work aims to directly use MR images taken shortly after injury to detect whether a patient suffers from mTBI, by incorporating machine learning and computer vision techniques to learn features suitable discriminating between mTBI and normal patients. We focus on 3 regions in brain, and extract multiple patches from them, and use bag-of-visual-word technique to represent each subject as a histogram of representative patterns derived from patches from all training subjects. After extracting the features, we use greedy forward feature selection, to choose a subset of features which achieves highest accuracy. We show through experimental studies that BoW features perform better than the simple mean value features which were used previously.

cs.CV↗