arXiv subjects

Xueli Wang

Publications and source records attributed to Xueli Wang.

11 recordsLinked to original sources

arXiv2026

FLaG: Frequency-Domain Latent-attention Gated Pooling for Token Aggregation

Token aggregation converts token-level representations into fixed-dimensional sample representations, but most pooling methods operate only in the original token space. We introduce Frequency-Domain Latent-attention Gated Pooling (FLaG), a plug-in aggregation module that re-expresses encoder outputs in the Fourier domain before final pooling. FLaG represents the nonredundant rFFT spectrum through concatenated real and imaginary components, summarizes spectral tokens with learnable latent queries, derives a sample-conditioned channel gate, and reconstructs modulated token representations for downstream aggregation. We evaluate the same architecture across ESM2-based antimicrobial peptide (AMP) activity prediction, ResNet18 image classification on CIFAR-10 and CIFAR-100, and three RoBERTa-based language tasks. FLaG achieves the best macro-averaged Spearman correlation coefficient, RMSE, and Recall@50 across four AMP backbone-species settings and the highest top-1 accuracy on CIFAR 10. It also achieves the best mean results on five of seven language metrics, although mean pooling remains strongest on STSBenchmark. AMP-side mechanistic analyses reveal low-frequency prediction sensitivity across most encoder layers, with increased relative high-frequency sensitivity in the final layer, and pronounced peptide-specific positional responses. The residual gate broadly amplifies spectral channels while preserving the low-frequency-dominated energy profile, whereas latent cross-attention exhibits sample- and species-specific spectral allocation. Overall, FLaG provides a transferable frequency-domain aggregation bias across protein, visual, and textual representations, with benefits that depend on the backbone and downstream task. Supplementary materials, source code, and data are available at https://www.healthinformaticslab.org/supp/ and https://github.com/Kewei2023/AMPCliff/tree/FLaG.

cs.AI↗

arXiv2026

CMCNet: Aligning Ultrasound Image Embeddings with Textual TI-RADS Representations for Fine-Grained Thyroid Classification

Ultrasound is the primary imaging modality for assessing thyroid nodules, and the ACR TI-RADS framework standardizes diagnosis through five ultrasound feature categories that are aggregated into five risk levels (TR1-TR5). Although widely adopted in clinical practice, most deep learning approaches focus on binary malignancy classification, while multi-class prediction and explicit utilization of feature-level supervision remain underexplored, largely due to limited annotated data. In this study, we introduce the STN dataset of 600 thyroid nodules with paired transverse and longitudinal ultrasound images, bounding box annotations, and complete labels for all five TI-RADS feature categories. Following the clinical decision process, we investigate how structured feature information can guide representation learning during training while requiring only images at inference. We demonstrate that text embeddings derived from standardized feature descriptions form a stable surrogate representation for TI-RADS risk levels. Based on this observation, we propose CMCNet, which aligns image embeddings to fixed textual embeddings via a Center-Margin Contrastive Loss that simultaneously promotes intra-class compactness and inter-class separation. Experimental results show that this embedding alignment strategy is more data-efficient and robust than direct multitask learning, and consistently outperforms InfoNCE, center loss, a strong multitask baseline, and a VQA-style multimodal model, particularly in imbalanced settings. The dataset is freely available at doi: 10.5281/zenodo.19125693 and the source code is available at: https://www.healthinformaticslab.org/supp/.

cs.CV↗

arXiv2026

Mediation Analysis with Multiple Mediators Subject to Missing Not at Random

Causal mediation analysis serves as a key tool for uncovering the mediating mechanisms linking treatments to outcomes. Existing methods for mediation analysis with multiple mediators typically assume complete observations or missing-at-random and may yield biased estimation when mediator values are missing not at random (MNAR). This paper studies the identification and estimation of causal mediation effects with multiple mediators subject to MNAR missingness. We consider a broad class of MNAR mechanisms in which missingness may depend on unobserved mediators, treatment, covariates, and outcomes. Under a series of increasingly general MNAR mechanisms, we establish identified natural direct and indirect effects, effectively generalizing existing mediation analysis to handle nonignorable missing mediators. Based on the proposed identification framework, we develop estimation procedures for causal mediation effects and evaluate their finite-sample performance through simulation studies. The results demonstrate satisfactory performance across a range of missingness scenarios. An application to data from the National Health and Nutrition Examination Survey(NHANES) illustrates the practical utility of the proposed methodology for investigating mediation pathways in the presence of nonignorable missing data.

stat.ME↗

arXiv2026

Frequency-Domain Latent Attention Gating for Cross-Domain Token Aggregation

Token aggregation is a common bottleneck in models that map token representations to sample-level predictions, yet most pooling methods operate only in the original token domain. We propose FLaG, a plug-in aggregation module that transforms token representations with the real FFT, summarizes spectral components with learnable latent queries, applies a channel-wise gate, and reconstructs enhanced time-domain tokens for final pooling. We evaluate FLaG on antimicrobial peptide (AMP) activity prediction with ESM2, image classification with ResNet18 on CIFAR-10 and CIFAR-100, and text classification with RoBERTa on IMDB and GLUE. FLaG achieves its clearest gains on the ESM2-8M antimicrobial peptide tasks and on CIFAR-100, while remaining competitive with strong text baselines on IMDB and GLUE. Then we probe its behavior on the AMP setting with band knockouts, gate summaries, residue perturbations, latent-query readouts, and structure-proxy stratification. We find that low-frequency bands contribute the most overall, and the remaining higher-band pattern is more sample-specific. The gate acts as a broadly shared spectral reweighting stage and the cross-attention patterns are sample-specific with mild query-wise differentiation, and higher-helix peptides exhibit stronger average spectral sensitivity in both bacteria. The supplementary materials, source code and data are released at https://www.healthinformaticslab.org/supp/ and https://github.com/Kewei2023/AMPCliff/tree/FLaG.

cs.LG↗

arXiv2026

Assessing Interactive Causes of an Occurred Outcome Due to Two Binary Exposures

In contrast to evaluating treatment effects, causal attribution analysis focuses on identifying the key factors responsible for an observed outcome. For two binary exposure variables and a binary outcome variable, researchers need to assess not only the likelihood that an observed outcome was caused by a particular exposure, but also the likelihood that it resulted from the interaction between the two exposures. For example, in the case of a male worker who smoked, was exposed to asbestos, and developed lung cancer, researchers aim to explore whether the cancer resulted from smoking, asbestos exposure, or their interaction. Even in randomized controlled trials, widely regarded as the gold standard for causal inference, identifying and evaluating retrospective causal interactions between two exposures remains challenging. In this paper, we define posterior probabilities to characterize the interactive causes of an observed outcome. We establish the identifiability of posterior probabilities by using a secondary outcome variable that may appear after the primary outcome. We apply the proposed method to the classic case of smoking and asbestos exposure. Our results indicate that for lung cancer patients who smoked and were exposed to asbestos, the disease is primarily attributable to the synergistic effect between smoking and asbestos exposure.

stat.AP↗

arXiv2025

Spin-polarized chiral ZnIn2S4 for targeted solar-driven CO2 reduction to acetic acid

Acetic acid, an important industrial chemical, is a key target product for CO2 reduction due to its dual role in carbon utilization and chemical feedstock supply. Although photocatalytic CO2 reduction (PCCR) can generate acetic acid alongside other multicarbon products, its yield is typically low, limited by competing reactions and inefficient C-C coupling. Herein, we report a chiral mesostructured ZnIn2S4 (CMZI) photocatalyst that achieves a remarkable acetic acid yield of 962 {umol g-1 h-1 with a high selectivity of 97.3 %. This yield is ten times higher than the current highest reported value, while attaining state-of-the-art selectivity10. The remarkable productivity arises from synergistic effect between chiral structure and sulfur (S) sites of CMZI. Chirality-induced spin polarization in CMZI stabilizes the key triplet OCCO intermediate, significantly promoting C-C coupling efficiency. Theoretical calculations reveal that the S sites on {102} crystal facets of ZnIn2S4 exhibit thermodynamic and kinetic preferences for acetic acid formation. This work offers critical insights into catalytic strategies for CO2 reduction toward the efficient and scalable synthesis of various multicarbon products.

cond-mat.mtrl-sci↗

arXiv2024

Efficiency-improved doubly robust estimation with non-confounding predictive covariates

In observational studies, covariates with substantial missing data are often omitted, despite their strong predictive capabilities. These excluded covariates are generally believed not to simultaneously affect both treatment and outcome, indicating that they are not genuine confounders and do not impact the identification of the average treatment effect (ATE). In this paper, we introduce an alternative doubly robust (DR) estimator that fully leverages non-confounding predictive covariates to enhance efficiency, while also allowing missing values in such covariates. Beyond the double robustness property, our proposed estimator is designed to be more efficient than the standard DR estimator. Specifically, when the propensity score model is correctly specified, it achieves the smallest asymptotic variance among the class of DR estimators, and brings additional efficiency gains by further integrating predictive covariates. Simulation studies demonstrate the notable performance of the proposed estimator over current popular methods. An illustrative example is provided to assess the effectiveness of right heart catheterization (RHC) for critically ill patients.

stat.ME↗

arXiv2021

Tunable mid-infrared hyperbolic van der Waals metasurfaces by strong plasmon-phonon polaritons coupling

Hyperbolic metasurfaces based on van der Waals (vdW) materials support propagation of extremely anisotropic polaritons towards nanoscale light compression and manipulation, and thus has great potential in the applications of planar hyperlens, nanolasing, quantum optics and ultrasensitive infrared spectroscopy. Two-dimensional hexagonal boron nitride (h-BN) as a vdW metasurface can manipulate the propagation of hyperbolic polaritons at the level of single atomic layers, possessing higher degree of field confinement and lower losses than the conventional media. However, active manipulation of hyperbolic polaritonic waves in h-BN midinfrared metasurfaces remains elusive. Herein, we provide an effective strategy for constructing tunable mid-infrared hyperbolic vdW metasurfaces (HMSs). They are composed of meta-atoms that are the in-plane heterostructures of thin-layer h-BN and monolayer graphene strips (iHBNG). The strong coupling of h-BN phonons and graphene plasmons enables the large tunability of light fields by tailoring chemical potentials of graphene without frequency shift, which involves topological transitions of polaritonic modes, unidirectional polariton propagation and local-density-of-state enhancement. Simulated visual near-field distributions of iHBNG metasurfaces reveal the unique transformations of hyperbolic polariton propagations, distinguished from that of individual h-BN and graphene metasurfaces. Our findings provide a platform of optical nanomanipulation towards emerging on-chip polaritonic devices.

physics.optics↗

arXiv2019

Threshold Trapdoor Functions and Their Applications

We introduce a cryptographic primitive named threshold trapdoor functions (TTDFs), from which we give generic constructions of threshold and revocation encryptions under adaptive corruption model. Then, we show TTDF can be instantiated under the decisional Diffie-Hellman (DDH) assumption and the learning with errors (LWE) assumption. By combining the instantiations of TTDF with the generic constructions, we obtain threshold and revocation encryptions which compare favorably over existing schemes. The experimental results show that our proposed schemes are practical.

cs.CR↗

arXiv2016

A Luminous Peculiar Type Ia Supernova SN 2011hr: More Like SN 1991T or SN 2007if?

Photometric and spectroscopic observations of a slowly declining, luminous Type Ia supernova (SN Ia) SN 2011hr in the starburst galaxy NGC 2691 are presented. SN 2011hr is found to peak at $M_{B}=-19.84 \pm 0.40\,\rm{mag}$, with a post-maximum decline rate $Δ$m$_{15}$(B) = 0.92 $\pm$ 0.03\,$\rm{mag}$. From the maximum-light bolometric luminosity, $L=(2.30 \pm 0.90) \times 10^{43}\,\rm{erg\,s^{-1}}$, we estimate the mass of synthesized \Nifs\ in SN 2011hr to be $M(\rm{^{56}Ni})=1.11 \pm 0.43\,M_{\sun}$. SN 2011hr appears more luminous than SN 1991T at around maximum light, and the absorption features from its intermediate-mass elements (IMEs) are noticeably weaker than the latter at similar phases. Spectral modeling suggests that SN 2011hr has the IMEs of $\sim$\,0.07 M$_{\sun}$ in the outer ejecta, which is much lower than the typical value of normal SNe Ia (i.e., 0.3 -- 0.4 M$_{\sun}$) and is also lower than the value of SN 1991T (i.e., $\sim$\,0.18 M$_{\sun}$). These results indicate that SN 2011hr may arise from a Chandrasekhar-mass white dwarf progenitor that experienced a more efficient burning process in the explosion. Nevertheless, it is still possible that SN 2011hr may serve as a transitional object connecting the SN 1991T-like SNe Ia with the superluminous subclass like SN 2007if given that the latter also shows very weak IMEs at all phases.

astro-ph.SR↗

arXiv2014

Optical and Ultraviolet Observations of A Low-Velocity Type II-Plateau Supernova 2013am in M65

Optical and ultraviolet observations for the nearby type II-plateau supernova (SN IIP) 2013am in the nearby spiral galaxy M65 are presented in this paper. The early spectra are characterized by relatively narrow P-Cygni features, with ejecta velocities much lower than observed in normal SNe IIP (i.e., $\sim$2000 km s$^{-1}$ vs. $\sim$5000 km $^{-1}$ in the middle of the plateau phase). Moreover, prominent Ca II absorptions are also detected in SN 2013am at relatively early phases. These spectral features are reminiscent of those seen in the low-velocity and low-luminosity SN IIP 2005cs. However, SN 2013am exhibits different photometric properties, having shorter plateau phases and brighter light-curve tails if compared to SN 2005cs. Adopting $R_{V}$=3.1 and a mean value of total reddening derived from the photometric and spectroscopic methods(i.e., $E(B-V)=0.55\pm$0.19 mag), we find that SN 2013am may have reached an absolute $V$-band peak magnitude of $-15.83\pm0.71$ mag, and produced a $^{56}$Ni mass of $0.016^{+0.010}_{-0.006} solar masses in the explosion. These parameters are close to those derived for SN 2008in and SN 2009N which have been regarded as "gap-filler" objects linking the faint SNe IIP to the normal ones. This indicates that some low-velocity SNe IIP may not necessarily result from the low-energetic explosions, and the low expansion velocities could be due to a lower metallicity of the progenitor stars, a larger envelope mass ejected in the explosion, or that is was observed at an angle that is away from the polar direction.

astro-ph.SR↗