Searcharxiv⌕ Search

arXiv subjects

Weining Wang

Publications and source records attributed to Weining Wang.

At least 19 recordsLinked to original sources
arXiv2026

Patch Attention Wisely: Understanding Patch Length in Attention-Based Forecasting

Attention-based time series forecasters commonly group consecutive observations into patches. Patch length is known to have a substantial impact on forecasting performance, yet its selection remains largely empirical. We develop a theoretical framework that explains why patch length matters for forecasting accuracy and provides a principled basis for its selection. For linear state-space models, we derive an exact factorization of the forecasting coefficient matrix that separates forecast dynamics from filtering dynamics. We show that dominance of a single forecast component at long horizons does not generally imply a rank-one representation. This explains why longer horizons alone need not reduce representational complexity. We combine the factorization with estimation bounds to develop a patch-selection criterion that balances representation and estimation errors under temporal dependence. Our analysis establishes conditions under which balanced patching is justified and clarifies how predictive structure, head count, training sample size, and long-run dependence enter the selection criterion.

stat.ML↗
arXiv2026

Estimating Network Spillovers under Dense Measurement Error

This paper analyzes spillover effects in spatial (network) models when the neighborhood (adjacency) matrix is contaminated by measurement error from reporting, aggregation, or disclosure imperfections, leading to inconsistent estimation of network effects. We introduce a regularization framework for the latent network that allows for sparse and/or low-rank structure and accommodates potential correlation between measurement errors and outcomes. We propose two estimators: (i) a two-stage procedure that first denoises the adjacency matrix and then incorporates the purified network into a regression analysis, and (ii) a Generalized Method of Moments (GMM) estimator that jointly estimates regression parameters and refines the network structure. We then establish strictly improved consistency rates for the spillover effect estimator relative to naive estimation ignoring measurement error. Simulations demonstrate that, in the presence of noisy networks, our approach reduces the root mean squared error of spillover estimates relative to conventional methods by approximately $50-80\%$. We apply our framework to examine the international spillover of economic growth, and the tax competition across U.S. states, illustrating that denoising might restore Leontief stability and yields improved estimates of spillovers.

econ.EM↗
arXiv2026

DiFuse: Fusing Native Diffusion Representations for Spatial Reasoning in Unified Multimodal Models

Unified multimodal models (UMMs) jointly support visual understanding and image generation, yet information flow between these two capabilities remains largely asymmetric: understanding representations routinely condition generation, whereas generative representations are rarely reused for multimodal reasoning. In this work, we investigate whether intermediate representations from a UMM's native diffusion branch can enhance spatial reasoning without compromising general multimodal understanding. We propose DiFuse, which selectively incorporates intermediate diffusion representations into the understanding pathway of UMMs. Through systematic layer-wise analysis, we identify which diffusion representations are most informative and where they can be integrated with minimal interference to semantic processing. Guided by these findings, DiFuse spatially aligns diffusion features with visual tokens and injects them into selected multimodal decoder layers via residual fusion. Extensive experiments on UniWorld-V1 show that, DiFuse consistently improves spatial reasoning over a matched SFT baseline while maintaining broadly comparable performance on general multimodal benchmarks. Further analyses show that these gains depend critically on the choice of diffusion representations, injection positions, and the preservation of spatial correspondence between diffusion features and visual tokens. Results on OmniGen2 further demonstrate the transferability of DiFuse across unified multimodal architectures. Overall, our findings show that native diffusion representations can provide complementary spatial cues for multimodal reasoning when selectively integrated in a structure-preserving manner.

cs.CV↗
arXiv2026

Simulation and Deep Learning Inversion for Full-sky Energetic Neutral Atom Imaging at the Heliospheric Boundary

The distribution of energetic neutral atom (ENA) differential flux density at the heliospheric boundary is the key to revealing the interaction mechanism between the solar wind and the interstellar medium. The Helios ENA Rapid Mapper (HERMA) is a pre-research project for a new ENA detection concept and technical principle, which is designed to provide technical support for refined detection with its advantages of wide energy range coverage and high spatial resolution. To verify the high spatiotemporal resolution rapid imaging capability of the HERMA, this study restored the particle response characteristics of the HERMA (spatial modulation grid + 256-pixel linear array silicon detector) based on Geant4 simulation, and we compared the performance of the traditional inversion algorithm with the convolutional neural network (CNN) inversion algorithm using INCA data as the benchmark. The results show that under different sampling times, the source distribution inverted by the CNN algorithm has a higher degree of agreement with the ideally expected distribution, and the CNN algorithm exhibits better stability and accuracy than the traditional algorithm under the conditions of low signal-to-noise ratio and short staring time. This study provides core technical support for the engineering verification and on-orbit application of the HERMA instrument, fills the technical gap in wide-energy-range and high-resolution ENA detection, and helps to deepen the research on the interaction mechanism between the solar wind and the interstellar medium at the heliospheric boundary.

astro-ph.IM↗
arXiv2026

Beta-Sorted Portfolios

Beta-sorted portfolios---portfolios comprised of assets with similar covariation with selected risk factors---are a popular tool in empirical finance to analyze models of (conditional) expected returns. Despite their widespread use, little is known of their econometric properties in contrast to comparable procedures such as two-pass regressions. We formally investigate the properties of beta-sorted portfolio returns by casting the procedure as a two-step nonparametric estimator with a nonparametric first step and a beta-adaptive portfolio construction. Our framework rationalizes the well-known estimation algorithm with precise economic and statistical assumptions on the general data-generating process. We provide conditions which ensure valid estimation and inference allowing for a range of hypotheses of interest in financial applications. We show that the rate of convergence of the estimator changes depending on the value of beta. We demonstrate that valid inference depends critically on the object of interest and discuss drawbacks of the widely used Fama-MacBeth variance estimator. To address these limitations, we propose a new variance estimator. We demonstrate the usefulness of our theoretical results in two empirical applications, including one in which we introduce a novel risk factor that captures the business credit cycle and show that it predicts both the cross-sectional and time-series behavior of U.S. stock returns.

econ.EM↗
arXiv2026

Train Where the Quantized Model Goes: On-Policy Distillation for Low-Bit Reasoning

Quantization-aware distillation (QAD) restores much of the short-form question-answering performance lost to sub-3-bit quantization, yet leaves mathematical and code reasoning substantially impaired. Long generations often degenerate into repetitive loops, exhausting the decoding budget without completing a solution. We trace this gap to quantization-amplified exposure bias: QAD trains on fixed corpus prefixes, while quantization-induced deviations compound along the model's own autoregressive trajectories. To address this mismatch, we introduce an on-policy distillation (OPD) stage that places teacher supervision where the quantized model actually goes. Starting from a QAD checkpoint, the student generates through the quantized forward path used at deployment and receives feedback from a frozen full-precision teacher on its own prefixes, combining dense token-level guidance with task-verifier rewards. Across four models at 2.79 and 1.88 effective bits, OPD raises average BF16 performance retention from 35% to 70% on MATH-500 and from 66% to 91% on HumanEval while preserving short-form performance, with reasoning gains substantially exceeding those of continued teacher-forced QAD in matched-budget comparisons. By coupling QAD's stable low-bit initialization with OPD's on-policy reasoning recovery, our framework provides a comprehensive sub-3-bit solution that preserves broad capabilities while restoring long-form reasoning.

cs.LG↗
arXiv2026

Causal State-Dependent Local Projections

State-dependent local projections (LPs) are widely used to study how causal effects vary as a function of economic states, but shock exogeneity alone does not identify this response function. We show that identification follows when the underlying conditional mean is linear in the shock with a state-dependent coefficient, a condition satisfied in canonical micro-macro environments, including first-order perturbation solutions of heterogeneous-agent and macro-finance models. Even then, standard linear-interaction LPs generally recover only a projection of the response function, motivating LPs with nonparametric state dependence. We develop a sieve estimator and establish pointwise and uniform inference for micro-macro panels, where a distinctive challenge is that the estimator can converge at different rates across the state space. Applied to firm investment, the method uncovers a hump-shaped response to monetary policy shocks and shows that standard linear-interaction LPs substantially understate the aggregate role of financial heterogeneity.

econ.EM↗
arXiv2026

Primitive-Driven Compositional Forensic Visual Prompting for Open-World Face Anti-Spoofing

Open-world face anti-spoofing must address both covariate and semantic shifts: source and target domains differ in imaging conditions, while target domains contain diverse attack types absent from training. Existing prompt-based approaches often express spoofing through category semantics or language guidance, which is effective for modeling high-level concepts but is less suited to explicitly capturing the evolving fine-grained and spatially heterogeneous forensic evidence of unseen attacks. Motivated by the hypothesis that many unseen attacks can be characterized by new combinations of recurring visual cues, we propose a compositional forensic visual prompt learning framework that operates entirely in the visual feature space. Built on a frozen ViT-based vision foundation model, the framework employs patch-aware attention to refine a shared set of learnable micro-forensic primitives into localized forensic evidence units derived from image patches. Class-specific global contextual prompts then provide input-dependent routing weights that adaptively select and compose these primitives into compositional forensic visual prompts for real/spoof discrimination. The primitives are not assigned predefined semantic meanings; instead, their specialization and reuse emerge from shared parameterization and joint optimization across categories. Extensive experiments on nine open-world protocols demonstrate state-of-the-art performance, strong cross-domain generalization, and robust adaptation to unseen attacks.

cs.CV↗
arXiv2026

Arellano-Bond LASSO Estimator for Dynamic Linear Panel Models

The Arellano-Bond estimator is a fundamental method for dynamic panel data models, widely used in practice. It can be severely biased when the time series dimension of the data, $T$, is long. The source of the bias is the large degree of overidentification. We propose a simple two-step approach to deal with this problem. The first step applies LASSO to the cross-section data at each time period to select the most informative moment conditions, exploiting the approximately sparse structure of these conditions. The second step applies a linear instrumental variable estimator using the instruments constructed from the moment conditions selected in the first step. Using asymptotic sequences where the two dimensions of the panel grow with the sample size, we show that the new estimator is consistent and asymptotically normal under much weaker conditions on $T$ than the Arellano-Bond estimator. Our theory covers models with high-dimensional covariates including multiple lags of the dependent variable and strictly exogenous covariates, which are becoming common in modern applications. We illustrate our approach by applying it to weekly county-level panel data from the United States to study opening K-12 schools and other mitigation policies' short and long-term effects on COVID-19's spread.

econ.EM↗
arXiv2026

Experimental Observation of Ghost Image Revivals via Structured Coherence

Ghost imaging retrieves an object's image from intensity correlations between two light beams, neither of which independently carries information about the object. However, conventional ghost imaging critically relies on precise object positioning and conjugate matching between the two arms, causing the image to disappear when these conditions are violated and the object is accessible from one plane only. In this Letter, we break this fundamental limitation by reporting the first experimental observation of revivals of ghost images of arbitrary objects via engineering the longitudinal intensity autocorrelation of a structured thermal light field into a coherence comb. With the reference arm fixed, translating the object produces periodic revivals of the ghost image whenever the object position matches a comb-tooth position, reminiscent of the Talbot effect. This capability enhances the flexibility of correlation imaging, enabling robust tomographic imaging of moving and non-periodic complex objects.

physics.optics↗
arXiv2026

Radially correlated partially coherent beams with a deterministic vortex structure

Partially coherent beams have attracted considerable attention due to their intrinsic resilience against complex environmental perturbations. However, the intrinsic wavefront fluctuations make it fundamentally challenging to preserve well-defined orbital angular momentum during propagation. In this work, we propose and experimentally demonstrate a class of radially correlated, partially coherent beams that carry deterministic vortex structures, generated via optical conformal mapping from Cartesian to log-polar coordinates. The resulting beams exhibit a ring-shaped coherence distribution, characterized by low coherence in the radial direction and high coherence in the azimuthal direction. This unique feature of such a beam supports a well-defined deterministic vortex phase, thereby enabling the beam to preserve its ring-shaped coherence distribution during propagation through a focusing system. Our results provide new insights into the design of new partially coherent beams and may facilitate the development of applications in optical encoding, free-space information transmission, and ultrafast light-matter interactions.

physics.optics↗
arXiv2026

From Vector Autoregressions to AI-based Time Series Forecasting: A Review

Forecasting is a central goal of time-series analysis. This review centers on three major developments in recent AI-based time-series forecasting: transformers, large pretrained models for zero-shot forecasting, and diffusion-based generative forecasters. We connect these methods to the econometric tradition built around the vector autoregression (VAR) through a common object: the conditional distribution of the future given the past. The review is organized around three long-standing challenges: \emph{high dimensionality}, \emph{nonstationarity}, and \emph{nonlinearity}. We argue that modern methods make progress by expanding the classical forecasting template: they allow more flexible dynamics, use larger information sets and training corpora, and represent richer predictive distributions. Yet they often lack the inferential and structural tools that make classical models useful for testing, explanation, and policy analysis. We close by outlining open problems where econometric tools remain important.

econ.EM↗
arXiv2026

High-dimensional inference on jumps in nonparametric time series regression models

We study simultaneous inference on jumps in the conditional mean functions of a high-dimensional collection of heterogeneous nonparametric time series, where the number of series may exceed the sample size and the data may exhibit strong cross-sectional dependence. The jump depends on one specific covariate, and we allow the regression function to vary with additional latent variables. We propose two uniform tests: one for the existence of jumps and one for their homogeneity across series. We derive a simple closed-form approximation to the covariance structure of the jump estimators and establish a high-dimensional Gaussian approximation showing that, owing to the localized construction of the statistics, the maximum of the studentized jumps is approximated by the maximum of independent Gaussians. The cross-sectional dependence is thus asymptotically negligible for critical values, even under strong (e.g., factor) dependence, and the approximation requires estimating only the variance for each series. For pronounced cross-sectional dependence, a dependence-aware refinement restores the off-diagonal covariances, improving finite-sample size and power. Simulations show accurate size and reasonable power under both cross-sectional and serial dependence, and two empirical applications reveal significant non-smooth effects.

econ.EM↗
arXiv2026

Policy Choice in Time Series by Empirical Welfare Maximization

This paper develops a novel method for policy choice in a dynamic setting where the available data is a multivariate time series. Overcoming challenges unique to time-series setting such as time-varying environments, history-dependent welfare, dynamic causal effects, and statistical dependence, we propose Time-series Empirical Welfare Maximization (T-EWM) methods. We characterize conditions for T-EWM to consistently learn optimal policies conditional or unconditional on the time-series history, and derive nonasymptotic upper bounds for the welfare regrets. We illustrate a use of T-EWM for optimal restriction rules against Covid-19.

econ.EM↗
arXiv2026

Imaging magnetically driven astrospheres: a forward modelling approach

An astrosphere is a vast, tailed bubble-like volume around a star, formed through the interaction between the stellar magnetic field, the stellar wind, and the interstellar medium (ISM). Detecting and characterizing astrospheres are essential for constraining stellar wind properties, understanding stellar evolution, and assessing the habitability of surrounding exoplanetary systems. Charge exchanges between ionized stellar wind particles and cold ISM hydrogen atoms populate the astrosphere with neutral hydrogen, which can leave observable signatures in the Lyman-$α$ (Ly$α$) line absorption profile. Previous studies have inferred stellar mass-loss rates by measuring Ly$α$ absorption in stellar spectra caused by astrospheric neutral hydrogen. However, our knowledge of the global morphology of astrospheres remains limited and largely dependent on sometimes contradictory simulations. Here we investigate the feasibility of detecting Ly$α$ emission generated by resonant scattering from \NH{} surrounding the star, enabling the construction of a two-dimensional map of the astrosphere. With a three-dimensional magnetohydrodynamic astrosphere model, we perform forward modelling of the Ly$α$ emission and assess the observation feasibility according to the observational limits of the {\it Hubble Space Telescope} (HST). We further discuss the influence of varied line-of-sight orientations and averaged ISM velocity along the line-of-sight. The spatially resolved circumstellar Ly$α$ emission could provide important constraints on the astrospheric configuration and stellar wind properties, such as the bow shock standing distance, the stellar wind symmetry, and the shape of the astro-tail. Our results highlight Ly$α$ astrosphere detections as a promising science case for {\it HST} and future missions such as the \textit{Habitable Worlds Observatory}.}

astro-ph.SR↗
arXiv2026

AGC: Adaptive Geodesic Correction for Adversarial Robustness on Vision-Language Models

Vision-language models like CLIP have demonstrated remarkable zero-shot transfer capabilities. However, their susceptibility to imperceptible adversarial perturbations remains a critical security concern. While test-time defenses offer a pragmatic solution for deployed models, existing approaches typically rely on gradient-based optimization during inference, incurring significant computational overhead. In this paper, we revisit the role of data augmentation in CLIP robustness and observe that augmentations are not equally effective: specific augmentations consistently provide robust geometric cues that align with correct class semantics in the hyperspherical feature space. Based on this, we propose Adaptive Geodesic Correction (AGC), a training-free defense mechanism that requires no parameter updates. AGC identifies a reliable augmentation as a geometric anchor and corrects the input feature towards it, utilizing an adaptive step size to balance robustness against clean accuracy preservation. AGC achieves superior performance across eight fine-grained datasets and three CLIP backbones, improving average robust accuracy by 44.4\% over state-of-the-art baseline while delivering a 10$\times$ reduction in inference latency. Our findings reveal a fundamental geometric property of CLIP features, offering a highly efficient and effective paradigm for robust multimodal deployment.

cs.CV↗
arXiv2026

Plausible GMM: A Quasi-Bayesian Approach

Structural estimation in economics often makes use of models formulated in terms of moment conditions. While these moment conditions are generally well-motivated, it is often unknown whether the moment restrictions hold exactly. We consider a framework where researchers model their belief about the potential degree of misspecification via a prior distribution and adopt a quasi-Bayesian approach for performing inference on structural parameters. We provide quasi-posterior concentration results, verify that quasi-posteriors can be used to obtain approximately optimal Bayesian decision rules under the maintained prior structure over misspecification, and provide a form of frequentist coverage results. We illustrate the approach through empirical examples where we obtain informative inference for structural objects allowing for substantial relaxations of the requirement that moment conditions hold exactly.

econ.EM↗
arXiv2026

Towards High Fidelity Face Swapping: A Comprehensive Survey and New Benchmark

Face swapping has witnessed significant progress in recent years, largely driven by advances in deep generative models such as GANs and diffusion models.Despite these advances, existing methods remain fragmented across different paradigms, and their evaluation is highly inconsistent due to the lack of standardized datasets and protocols. Moreover, prior surveys primarily focus on broader deepfake generation or detection, leaving face swapping insufficiently studied as a standalone problem. In this paper, we present a comprehensive survey and benchmark for face swapping. We provide a structured review of existing methods, organizing them into five major paradigms and systematically analyzing their design principles, strengths, and limitations. To enable fair and controlled evaluation, we introduce CASIA FaceSwapping, a high-quality benchmark with balanced demographic distributions and explicit attribute variations, and establish standardized protocols to assess the robustness of different face swapping methods. Extensive experiments on representative approaches yield new insights into the performance characteristics and limitations of current techniques. Overall, our work provides a unified perspective and a principled evaluation framework to facilitate the development of more robust and controllable face swapping methods. More results can be found at https://github.com/CASIA-NLPRAI/face-swapping-survey.

cs.CV↗