arXiv subjects

Wen Shi

Publications and source records attributed to Wen Shi.

17 recordsLinked to original sources

arXiv2026

Interpretable AI predicts a 2026 summer dry anomaly in central China

Seasonal precipitation anomalies are largely regulated by atmospheric circulation, which dynamical models predict with greater reliability than precipitation itself. Here, we employ a deep learning model that translates dynamical circulation predictions into precipitation estimates. Predictions initialized from March to May consistently indicate a dry anomaly over central China in summer 2026. Retrospective evaluations revealed higher predictive skill in the analogue years, which also tended to feature central equatorial Pacific warming persisting from the preceding winter into summer. This warming favors an anomalous cyclonic circulation over the western North Pacific-South China Sea-South China region, which induces northerly winds and moisture divergence that jointly suppress rainfall over central China. Supporting this mechanism, layer-wise relevance propagation (LRP) independently identifies these northerly winds as the dominant driver of the prediction among all model inputs. Perturbation tests supported this attribution: removing LRP-identified features effectively eliminates the dry anomaly. Our framework thus provides physically interpretable explanations for AI-derived regional climate projections, facilitating evidence-based assessment before observational data become available.

physics.ao-ph↗

arXiv2026

TERGAD: Structure-Aware Text-Enhanced Representations for Graph Anomaly Detection

Graph Anomaly Detection (GAD) aims to identify atypical graph entities, such as nodes, edges, or substructures, that deviate significantly from the majority. While existing text-rich approaches typically integrate structural context into the data representation pipeline using raw textual features, they often neglect the structural context of nodes. This limitation hinders their ability to detect sophisticated anomalies arising from inconsistencies between a node's inherent content and its topological role. To bridge this gap, we propose TERGAD (Structure-aware Text-enhanced Representations for Graph Anomaly Detection), A novel data augmentation framework that enriches structural semantics for GAD via the semantic reasoning capabilities of Large Language Models (LLMs). Specifically, TERGAD translates node-level topological properties into descriptive natural language narratives, which are subsequently processed by an LLM to derive high-level semantic embeddings. These embeddings are then adaptively fused with original node attributes through a gated dual-branch autoencoder to jointly reconstruct both graph structure and node features. The anomaly score is computed based on the integrated reconstruction error, effectively capturing deviations in both observable attributes and LLM-informed semantic expectations. Extensive experiments on six real-world datasets demonstrate that TERGAD consistently outperforms state-of-the-art baselines. Furthermore, our ablation studies validate the indispensable role of structural semantic guidance and the efficacy of the gated fusion mechanism. Code is available at https://github.com/Kantorakitty/TERGAD-main.

cs.CL↗

arXiv2026

FairGC: Fairness-aware Graph Condensation

Graph condensation (GC) has become a vital strategy for scaling Graph Neural Networks by compressing massive datasets into small, synthetic node sets. While current GC methods effectively maintain predictive accuracy, they are primarily designed for utility and often ignore fairness constraints. Because these techniques are bias-blind, they frequently capture and even amplify demographic disparities found in the original data. This leads to synthetic proxies that are unsuitable for sensitive applications like credit scoring or social recommendations. To solve this problem, we introduce FairGC, a unified framework that embeds fairness directly into the graph distillation process. Our approach consists of three key components. First, a Distribution-Preserving Condensation module synchronizes the joint distributions of labels and sensitive attributes to stop bias from spreading. Second, a Spectral Encoding module uses Laplacian eigen-decomposition to preserve essential global structural patterns. Finally, a Fairness-Enhanced Neural Architecture employs multi-domain fusion and a label-smoothing curriculum to produce equitable predictions. Rigorous evaluations on four real-world datasets, show that FairGC provides a superior balance between accuracy and fairness. Our results confirm that FairGC significantly reduces disparity in Statistical Parity and Equal Opportunity compared to existing state-of-the-art condensation models. The codes are available at https://github.com/LuoRenqiang/FairGC.

cs.LG↗

arXiv2026

Electric-current-assisted nucleation of zero-field hopfion rings

Magnetic hopfions are three-dimensional topological solitons -- knotted, vortex-like spin configurations. In chiral magnets, hopfions can appear as isolated structures or they can be linked to skyrmion strings. Previous studies employed a sophisticated protocol and a special sample geometry to nucleate such hopfions linked to one or a few skyrmion strings. Here, we introduce an electric-current-assisted nucleation protocol that is simple and independent of the sample shape and size. The resulting hopfions exhibit extraordinary stability in the presence of both positive and negative magnetic fields, in perfect agreement with micromagnetic simulations. We also present a comprehensive framework for classifying hopfions, skyrmions, and merons by deriving the corresponding homotopy group.

cond-mat.mes-hall↗

arXiv2026

Bridging Semantic Understanding and Popularity Bias with LLMs

Semantic understanding of popularity bias is a crucial yet underexplored challenge in recommender systems, where popular items are often favored at the expense of niche content. Most existing debiasing methods treat the semantic understanding of popularity bias as a matter of diversity enhancement or long-tail coverage, neglecting the deeper semantic layer that embodies the causal origins of the bias itself. Consequently, such shallow interpretations limit both their debiasing effectiveness and recommendation accuracy. In this paper, we propose FairLRM, a novel framework that bridges the gap in the semantic understanding of popularity bias with Recommendation via Large Language Model (RecLLM). FairLRM decomposes popularity bias into item-side and user-side components, using structured instruction-based prompts to enhance the model's comprehension of both global item distributions and individual user preferences. Unlike traditional methods that rely on surface-level features such as "diversity" or "debiasing", FairLRM improves the model's ability to semantically interpret and address the underlying bias. Through empirical evaluation, we show that FairLRM significantly enhances both fairness and recommendation accuracy, providing a more semantically aware and trustworthy approach to enhance the semantic understanding of popularity bias. The implementation is available at https://github.com/LuoRenqiang/FairLRM.

cs.IR↗

arXiv2025

HeartLLM: Discretized ECG Tokenization for LLM-Based Diagnostic Reasoning

Electrocardiography (ECG) plays a central role in cardiovascular diagnostics, yet existing automated approaches often struggle to generalize across clinical tasks and offer limited support for open-ended reasoning. We present HeartLLM, a novel framework that integrates time-series (TS) and language modeling by enabling large language models (LLMs) to process 12-lead ECG signals for clinical text generation tasks. Our approach discretizes continuous ECG embeddings into quantized codes using a lead-wise encoder and quantization module. These quantized codes are then mapped to an extended ECG vocabulary to form ECG tokens, enabling the model to process both ECG and natural language inputs within a unified framework. To bridge the modality gap, we pretrain the model on an autoregressive ECG token forecasting task, allowing the LLM to capture temporal dynamics through its inherent language modeling capability. Finally, we perform instruction tuning on both ECG question answering and diagnostic report generation. Without modifying the core model, HeartLLM achieves strong performance across tasks while maintaining generalization to out-of-distribution settings. Extensive experiments demonstrate the effectiveness of each component and highlight the potential of integrating discretized ECG tokens into LLMs for medical reasoning.

cs.AI↗

arXiv2025

Reconstruction of Antarctic sea ice thickness from sparse satellite laser altimetry data using a partial convolutional neural network

The persistent lack of spatially complete Antarctic sea ice thickness (SIT) data at sub-monthly resolution has fundamentally constrained the quantitative understanding of large-scale sea ice mass balance processes. In this study, a pan-Antarctic SIT dataset at 5-day and 12.5 km resolution was developed based on sparse Ice, Cloud and Land Elevation Satellite (ICESat: 2003-2009) and ICESat-2 (2018-2024) along-track laser altimetry SIT retrievals using a deep learning approach. The reconstructed SIT was quantitatively validated against independent upward-looking sonar (ULS) observations and showed higher accuracy than the other four satellite-derived and reanalyzed Antarctic SIT datasets. The temporal evolution of the reconstructed SIT was further validated by ULS and ICESat-2 observations. Consistent seasonal cycles and intra-seasonal tendencies across these datasets confirm the reconstruction's reliability. Beyond advancing the mechanistic understanding of Antarctic sea ice variability and climate linkages, this reconstruction dataset's near-real-time updating capability offers operational value for monitoring and forecasting the Antarctic sea ice state.

physics.geo-ph↗

arXiv2024

Bonding Hierarchy and Coordination Interaction Leading to High Thermoelectricity in Wide Bandgap TlAgI2

High thermoelectric properties are associated with the phonon-glass electron-crystal paradigm. Conventional wisdom suggests that the optimal bandgap of semiconductor to achieve the largest power factor should be between 6 and 10 kbT. To address challenges related to the bipolar effect and temperature limitations, we present findings on Zintl-type TlAgI2, which demonstrates an exceptionally low lattice thermal conductivity of 0.3 W m-1 K-1 at 300 K. The achieved figure of merit (ZT) for TlAgI2, featuring a 1.55 eV bandgap, reaches a value of 2.20 for p-type semiconductor. This remarkable ZT is attributed to the existence of extended antibonding states Ag-I in the valence band. Furthermore, the bonding hierarchy, influencing phonon anharmonicity, and coordination bonds, facilitating electron transfer between the ligand and the central metal ion, significantly contribute to electronic transport. This finding serves as a promising avenue for the development of high ZT materials with wide bandgaps at elevated temperatures.

cond-mat.mtrl-sci↗

arXiv2023

Direct observation of altermagnetic band splitting in CrSb thin films

Altermagnetism represents an emergent collinear magnetic phase with compensated order and an unconventional alternating even-parity wave spin order in the non-relativistic band structure. We investigate directly this unconventional band splitting near the Fermi energy through spinintegrated soft X-ray angular resolved photoemission spectroscopy. The experimentally obtained angle-dependent photoemission intensity, acquired from epitaxial thin films of the predicted altermagnet CrSb, demonstrates robust agreement with the corresponding band structure calculations. In particular, we observe the distinctive splitting of an electronic band on a low-symmetry path in the Brilliouin zone that connects two points featuring symmetry-induced degeneracy. The measured large magnitude of the spin splitting of approximately 0.6 eV and the position of the band just below the Fermi energy underscores the signifcance of altermagnets for spintronics based on robust broken time reversal symmetry responses arising from exchange energy scales, akin to ferromagnets, while remaining insensitive to external magnetic fields and possessing THz dynamics, akin to antiferromagnets.

cond-mat.mtrl-sci↗

arXiv2023

A Motion Assessment Method for Reference Stack Selection in Fetal Brain MRI Reconstruction Based on Tensor Rank Approximation

Purpose: Slice-to-volume registration and super-resolution reconstruction (SVR-SRR) is commonly used to generate 3D volumes of the fetal brain from 2D stacks of slices acquired in multiple orientations. A critical initial step in this pipeline is to select one stack with the minimum motion as a reference for registration. An accurate and unbiased motion assessment (MA) is thus crucial for successful selection. Methods: We presented a MA method that determines the minimum motion stack based on 3D low-rank approximation using CANDECOMP/PARAFAC (CP) decomposition. Compared to the current 2D singular value decomposition (SVD) based method that requires flattening stacks into matrices to obtain ranks, in which the spatial information is lost, the CP-based method can factorize 3D stack into low-rank and sparse components in a computationally efficient manner. The difference between the original stack and its low-rank approximation was proposed as the motion indicator. Results: Compared to SVD-based methods, our proposed CP-based MA demonstrated higher sensitivity in detecting small motion with a lower baseline bias. Experiments on randomly simulated motion illustrated that the proposed CP method achieved a higher success rate of 95.45% in identifying the minimum motion stack, compared to SVD-based method with a success rate of 58.18%. We further demonstrated that combining CP-based MA with existing SRR-SVR pipeline significantly improved 3D volume reconstruction. Conclusion: The proposed CP-based MA method showed superior performance compared to SVD-based methods with higher sensitivity to motion, success rate, and lower baseline bias, and can be used as a prior step to improve fetal brain reconstruction.

eess.IV↗

arXiv2023

Inter-brain substrates of role switching during mother-child interaction

Mother-child interaction is highly dynamic and reciprocal. Switching roles in these back-and-forth interactions serves as a crucial feature of reciprocal behaviors while the underlying neural entrainment is still not well-studied. Here, we designed a role-controlled cooperative task with dual EEG recording to study how differently two brains interact when mothers and children hold different roles. When children were actors and mothers were observers, mother-child inter-brain synchrony emerged within the theta oscillations and the frontal lobe, which highly correlated with children's attachment to their mothers. When their roles were reversed, this synchrony was shifted to the alpha oscillations and the central area and associated with mothers' perception of their relationship with their children. The results suggested an observer-actor neural alignment within the actor's oscillations, which was modulated by the actor-toward-observer emotional bonding. Our findings contribute to the understanding of how inter-brain synchrony is established and dynamically changed during mother-child reciprocal interaction.

q-bio.NC↗

arXiv2022

Integrating multi-type aberrations from DNA and RNA through dynamic mapping gene space for subtype-specific breast cancer driver discovery

Driver event discovery is a crucial demand for breast cancer diagnosis and therapy. Especially, discovering subtype-specificity of drivers can prompt the personalized biomarker discovery and precision treatment of cancer patients. still, most of the existing computational driver discovery studies mainly exploit the information from DNA aberrations and gene interactions. Notably, cancer driver events would occur due to not only DNA aberrations but also RNA alternations, but integrating multi-type aberrations from both DNA and RNA is still a challenging task for breast cancer drivers. On the one hand, the data formats of different aberration types also differ from each other, known as data format incompatibility. One the other hand, different types of aberrations demonstrate distinct patterns across samples, known as aberration type heterogeneity. To promote the integrated analysis of subtype-specific breast cancer drivers, we design a "splicing-and-fusing" framework to address the issues of data format incompatibility and aberration type heterogeneity respectively. To overcome the data format incompatibility, the "splicing-step" employs a knowledge graph structure to connect multi-type aberrations from the DNA and RNA data into a unified formation. To tackle the aberration type heterogeneity, the "fusing-step" adopts a dynamic mapping gene space integration approach to represent the multi-type information by vectorized profiles. The experiments also demonstrate the advantages of our approach in both the integration of multi-type aberrations from DNA and RNA and the discovery of subtype-specific breast cancer drivers. In summary, our "splicing-and-fusing" framework with knowledge graph connection and dynamic mapping gene space fusion of multi-type aberrations data from DNA and RNA can successfully discover potential breast cancer drivers with subtype-specificity indication.

q-bio.QM↗

arXiv2022

A microstructure estimation Transformer inspired by sparse representation for diffusion MRI

Diffusion magnetic resonance imaging (dMRI) is an important tool in characterizing tissue microstructure based on biophysical models, which are complex and highly non-linear. Resolving microstructures with optimization techniques is prone to estimation errors and requires dense sampling in the q-space. Deep learning based approaches have been proposed to overcome these limitations. Motivated by the superior performance of the Transformer, in this work, we present a learning-based framework based on Transformer, namely, a Microstructure Estimation Transformer with Sparse Coding (METSC) for dMRI-based microstructure estimation with downsampled q-space data. To take advantage of the Transformer while addressing its limitation in large training data requirements, we explicitly introduce an inductive bias - model bias into the Transformer using a sparse coding technique to facilitate the training process. Thus, the METSC is composed with three stages, an embedding stage, a sparse representation stage, and a mapping stage. The embedding stage is a Transformer-based structure that encodes the signal to ensure the voxel is represented effectively. In the sparse representation stage, a dictionary is constructed by solving a sparse reconstruction problem that unfolds the Iterative Hard Thresholding (IHT) process. The mapping stage is essentially a decoder that computes the microstructural parameters from the output of the second stage, based on the weighted sum of normalized dictionary coefficients where the weights are also learned. We tested our framework on two dMRI models with downsampled q-space data, including the intravoxel incoherent motion (IVIM) model and the neurite orientation dispersion and density imaging (NODDI) model. The proposed method achieved up to 11.25 folds of acceleration in scan time and outperformed the other state-of-the-art learning-based methods.

eess.SP↗

arXiv2022

AFFIRM: Affinity Fusion-based Framework for Iteratively Random Motion correction of multi-slice fetal brain MRI

Multi-slice magnetic resonance images of the fetal brain are usually contaminated by severe and arbitrary fetal and maternal motion. Hence, stable and robust motion correction is necessary to reconstruct high-resolution 3D fetal brain volume for clinical diagnosis and quantitative analysis. However, the conventional registration-based correction has a limited capture range and is insufficient for detecting relatively large motions. Here, we present a novel Affinity Fusion-based Framework for Iteratively Random Motion (AFFIRM) correction of the multi-slice fetal brain MRI. It learns the sequential motion from multiple stacks of slices and integrates the features between 2D slices and reconstructed 3D volume using affinity fusion, which resembles the iterations between slice-to-volume registration and volumetric reconstruction in the regular pipeline. The method accurately estimates the motion regardless of brain orientations and outperforms other state-of-the-art learning-based methods on the simulated motion-corrupted data, with a 48.4% reduction of mean absolute error for rotation and 61.3% for displacement. We then incorporated AFFIRM into the multi-resolution slice-to-volume registration and tested it on the real-world fetal MRI scans at different gestation stages. The results indicated that adding AFFIRM to the conventional pipeline improved the success rate of fetal brain super-resolution reconstruction from 77.2% to 91.9%.

eess.IV↗

arXiv2021

SNEAK: Synonymous Sentences-Aware Adversarial Attack on Natural Language Video Localization

Natural language video localization (NLVL) is an important task in the vision-language understanding area, which calls for an in-depth understanding of not only computer vision and natural language side alone, but more importantly the interplay between both sides. Adversarial vulnerability has been well-recognized as a critical security issue of deep neural network models, which requires prudent investigation. Despite its extensive yet separated studies in video and language tasks, current understanding of the adversarial robustness in vision-language joint tasks like NLVL is less developed. This paper therefore aims to comprehensively investigate the adversarial robustness of NLVL models by examining three facets of vulnerabilities from both attack and defense aspects. To achieve the attack goal, we propose a new adversarial attack paradigm called synonymous sentences-aware adversarial attack on NLVL (SNEAK), which captures the cross-modality interplay between the vision and language sides.

cs.CV↗

arXiv2020

Ab initio dipolar electron-phonon interactions in two-dimensional materials

We develop an ab initio formalism for dipolar electron-phonon interactions (EPI) in two-dimensional (2D) materials. Unlike purely longitudinal Fröhlich model, we show that the out-of-plane dipoles also contribute to the long-wavelength non-analytical behavior of EPI. And the 2D dipolar EPI plays an important role not only in the typical polar material MoS$_2$, but also in graphane and fluorinated graphene. By incorporating this formalism into Wannier-Fourier interpolation, we enable accurate EPI calculations for 2D materials and subsequent intrinsic carrier mobility prediction. The results show that Fröhlich model is inadequate for 2D materials and correct long-wavelength interaction must be included for the reliable prediction.

cond-mat.mtrl-sci↗

arXiv2018

Intrinsic Charge Transport in Stanene: Roles of Bucklings and Electron-Phonon Couplings

The intrinsic charge transport of stanene is investigated by using density function theory and density function perturbation theory coupled with Boltzmann transport equations from first principles. The accurate Wannier interpolations are applied to calculate the charge carrier scatterings with all branches of phonons with dispersion contribution. The intrinsic carrier mobilities are predicted to be 2~3$\times10^3$ cm$^2$/(V s) at 300 K, and we find that the intervalley scatterings from the out-of-plane and transverse acoustic phonon modes dominate the carrier relaxation. In contrast, the intrinsic carrier mobilities obtained by the conventional deformation potential approach (Long et al., J. Am. Chem. Soc. 2009, 131, 17728) are found to as large as 2~3$\times$10$^6$ cm$^2$/(V s) at 300 K, in which the longitudinal acoustic phonons are assumed to be the only scattering mechanism. The inadequacy of the deformation potential approximation in stanene is attributed to the buckling of the honeycomb structure, which originates from the $sp^2-sp^3$ orbital hybridization and results in broken mirror symmetry as compared to graphene. The high carrier mobility of stanene renders it a promising candidate in nanoelectronics and spintronics applications and we propose to enhance its carrier mobilities by suppressing the out-of-plane vibrations by substrate suspension or clamping.

physics.chem-ph↗