arXiv subjects

Shuo Huang

Publications and source records attributed to Shuo Huang.

At least 19 recordsLinked to original sources

arXiv2026

Quasi-Sinusoidal Single Diamond Structure in Royal Jewel Butterfly: An Angle-Independent Photonic Structure

Structural colouration with narrow spectral photonic bandwidth and high reflectivity is of critical importance for modern optical applications, including displays, laser systems, and optical sensing, etc. Achieving such angle independent colouration typically relies on polycrystalline or inherent structural disorder. However, balancing angular uniformity with high brightness and strong colour contrast remains challenging. Herein, we uncover the structural origin of the spectacular bright, angle-independent blue colouration of Hypochrysops polycletus, a sapphire-like Royal Jewel butterfly. Three-dimensional (3D) electron microscopy reveals that the dorsal wing scale has a single diamond structure, a 3D photonic crystal previously documented only in beetles and weevils. The crystal domains form an extraordinary quasi sinusoidal surface geometry with a distinct template morphology-guided arrangement. Unlike typically thicker biophotonic structures that support multiple high symmetry stopbands, this design contains only 3-4 unit cells in the propagation direction. Its optical response is dominated by the fundamental stopband, with two dominant scattering mechanisms: specular reflection at the {111} inclined sidewalls of the hierarchical structure, and funnelling into localised quasi-normal modes enabled by a strongly anisotropic Bloch transport. By mimicking these features with two-photon polymerisation, we artificially reproduced the optical response in the infrared region. The study opens a pathway towards bioinspired brilliant diffuse colouration and angle-robust photonic devices.

physics.optics↗

arXiv2026

When Is a Conformal Guarantee Fair? Auditing Silent Subgroup Under-Coverage in Alzheimer's Disease Longitudinal Prediction

Longitudinal prediction of Alzheimer's disease biomarkers increasingly informs clinical decisions, and a forecast is only useful if it also reports how much to trust it. Conformal prediction supplies this by wrapping any forecaster in a prediction band with a finite-sample coverage guarantee under exchangeability. However, standard population-level conformal prediction guarantees only marginal coverage and may mask substantial under-coverage within clinically important subgroups. We introduce a general mechanism-driven framework for auditing and repairing such subgroup under-coverage. Across two cohorts (ADNI, OASIS-3), two base forecasters, and nine attributes spanning genetic risk, demographics, and clinical severity, we find that population-level bands under-cover high-risk subgroups in 57 of 68 audited combinations, despite achieving nominal marginal coverage. We trace these failures to two mechanisms: (A) \emph{rarity}, where a group-conditional band calibrated on only $n$ patients covers at most $k/(n+1)$; and (B) \emph{tail-heaviness}, where a population-wide band is too narrow for a heavy-tailed subgroup and additional data cannot close the gap. Under-coverage falls disproportionately on patients with high genetic risk and disease severity (6.1 pp mean deficit, 95\% CI [3.3, 8.9]), while demographic groups remain at the target level on average (0.0 pp, CI [$-1.9$, 1.7]). We pair each mechanism with a corresponding conformal correction: cross-conformal pooling for rarity, per-subgroup calibration for tail-heaviness, and a coverage-safe marginal floor when both arise. Together, these corrections restore target coverage for nearly every high-risk subgroup across both cohorts and forecasters.

stat.ME↗

arXiv2026

DocPO: Advancing Document Policy Optimization via Tailored Step-Aware Rewards

Reinforcement learning (RL) for document parsing often relies on reference-based rewards rooted in edit distance (e.g., tree edit distance), yet it remains hard to optimize in the high-accuracy regime because such rewards become weakly discriminative: near-correct outputs receive very similar scores, providing limited learning signal for hard cases. We propose Step-Aware Annealing (SAA), a plug-and-play reward sharpening mechanism that progressively increases reward curvature during training, amplifying subtle quality differences among high-scoring samples while preserving stability in early learning. Built on SAA, we introduce DocPO, a document policy optimization framework with element-specific, reference-based rewards anchored by edit-distance signals: normalized string edit distance (NED) for text, tree edit distance similarity (TEDS) for tables, and a hybrid Rubric+edit reward for formulas. Experiments on OmniDocBench and DocElemHard show that SAA consistently improves GRPO-style RL across document elements over non-annealed rewards, without requiring additional human supervision for reward construction.

cs.CV↗

arXiv2026

TabPFN beyond Tabular Data: Calibration and Accuracy on Multimodal Embeddings

Few-shot multimodal classification commonly attaches a lightweight head, such as $k$-nearest neighbors, logistic regression, or a linear SVM, to a frozen pretrained encoder. Although computationally efficient, these heads can produce poorly calibrated confidence scores. We ask whether TabPFN can provide reliable confidence estimates on multimodal embeddings without sacrificing predictive accuracy, and under what conditions. We systematically evaluate TabPFN as a zero-gradient head for frozen image, text, and audio encoders. Across 22{,}820 evaluation episodes spanning 14 datasets, 11 encoders, and three modalities, TabPFN achieves the best mean rank among nine classification heads on both negative log-likelihood (NLL) and expected calibration error (ECE). At a representative setting, it reduces NLL by 48--62\% and ECE by 2.1--5.3$\times$ relative to the average of eight baselines while matching or exceeding their average accuracy. This calibration benefit transfers broadly, whereas the accuracy advantage is conditional: it concentrates at moderate-to-high shot counts and low-to-moderate feature dimensions ($k \ge 50$, $d \le 32$), and diminishes when labeled data are scarce, feature dimensions are high, or competing methods approach ceiling accuracy. After backbone adaptation, replacing the trained linear head with TabPFN improves calibration while preserving competitive accuracy, showing that representation adaptation and reliable head choice are complementary. Together, these results identify when TabPFN can serve as a training-free head for calibration-sensitive multimodal classification. To support transparency and reproducibility, we publicly release the source code, experiment configurations, and evaluation scripts in our GitHub repository: https://github.com/Jingxiang-Zhang/tabpfn-multimodal-embeddings.

cs.LG↗

arXiv2026

MORE: A Multilingual Document Parsing Benchmark and Evaluation

Multilingual documents encapsulate rich regional cultures, scientific discoveries, and historical records. Parsing this content into structured, machine-readable formats is critical for unlocking global knowledge. However, existing benchmarks predominantly focus on high-resource languages like English and Chinese, creating an evaluation blind spot concerning model performance on other languages. While recent Vision-Language Models (VLMs) claim support for hundreds of languages, the lack of ground truth makes it impossible to empirically verify these capabilities. To bridge this gap, we introduce MORE, a large-scale benchmark designed for multilingual document parsing evaluation. MORE distinguishes itself through three key dimensions: (1) Unprecedented Scale: It covers 149 languages, making it the most linguistically diverse benchmark to date; (2) Structural Complexity: Unlike previous works, it extends evaluation beyond plain text to include structural elements such as code blocks, tables, and catalogs; and (3) Data Authenticity: All samples are curated from real-world documents via a model-assisted, human-refined annotation pipeline. We evaluate state-of-the-art models using MORE, establishing new performance baselines for long-tail languages and validating the benchmark's effectiveness in diagnosing model capabilities in realistic, diverse scenarios. The MORE dataset will be available at https://github.com/zimoqingfeng/MORE.

cs.CV↗

arXiv2026

Dimension expansion for simulation-efficient nanophotonic neural networks

Inverse design of nanophotonic structures is challenging due to the large design space, nonlinear structure-response relationships, and the high computational cost of iterative electromagnetic simulations. Existing deep-learning approaches typically rely on large precomputed datasets or libraries of optimized structures, which limits scalability to continuous and complex inverse-design tasks. We introduce a Dimension Expansion Network (DEN), a fully unsupervised, simulation-efficient framework for nanophotonic inverse design. DEN addresses the mismatch between low-dimensional design objectives and high-dimensional nanophotonic structures by transforming compact target parameters into structured, high-dimensional conditioning representations before inverse design. This improves target expressivity and conditioning quality for structure generation. The model is trained end-to-end using differentiable electromagnetic simulations, removing the need for any pre-generated dataset. We validate DEN on free-form metalens and asymmetric Y-splitter design problems. For metalens design, DEN achieves focal intensities comparable to adjoint-based optimization while reducing simulation cost by approximately 50% and generalizing across tens to thousands of focal targets within a shared focal region. For Y-splitter design, DEN accurately produces arbitrary power-splitting ratios using only 21 training targets and demonstrates robust broadband performance. Ablation studies and representation analyses show that dimension expansion enhances sensitivity to target variations, increases structural diversity, and reduces mode-collapse-like behavior. Overall, DEN provides a scalable conditioning strategy for inverse design with low-dimensional objectives, enabling efficient photonic design across large continuous target spaces.

eess.IV↗

arXiv2026

A Surface-based Multimodal Framework for Multitask Analysis in Alzheimer's Disease

Alzheimer's Disease (AD) is a progressive neurodegenerative disorder, and longitudinal analysis is critical for early detection and effective intervention. Developing models capable of multimodal and multitask analysis enables a more comprehensive understanding of AD progression. However, multimodal learning remains challenged by cross-modal misalignment, non-Euclidean surface representations of cortical data, and limited data availability in small-sample clinical settings. In this work, we propose an augmented spherical data-driven multimodal framework for multitask AD analysis. A spherical diffusion model is first trained to generate paired cortical thickness and Tau PET Standardized Uptake Value Ratio (SUVR) data, enabling structurally consistent multimodal augmentation on cortical surfaces while preserving anatomical correspondence. The augmented data are subsequently used to train a contrastive learning model that learns aligned and fused cross-modal representations. This design strengthens multimodal integration and encourages more balanced representation learning. The learned imaging features are further integrated with tabular cognitive assessments and demographic variables, and processed using an in-context learning model to perform both classification and regression tasks without task-specific fine-tuning. Experiments on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset ($n = 802$) demonstrate consistent performance improvements across five diagnostic and longitudinal tasks, outperforming six baseline models.

eess.IV↗

arXiv2026

Acoustic radiation force on a liquid particle in a standing surface acoustic wave field

We develop a theory for the acoustic radiation force on a liquid particle in a 2D standing-wave field beyond the Rayleigh limit. The theory is valid for any frequency, includes the traveling-wave components due to the Rayleigh angle, and is thus applicable to a large class of surface acoustic wave applications. The analytical results are validated with respect to finite-element models. Using our analytical solution, we determine the parameter space for which Rayleigh-limit methods, such as the Gor'kov framework, remain applicable. This range is shown to depend on the particle properties, the Rayleigh angle, and even the particle position in the acoustic field. We propose a general form for the acoustophoretic contrast factor applicable to any wavelength of 1D standing-wave field, broadening the applicability of the classical Gor'kov framework. We show that the Rayleigh-angle effect can substantially weaken the acoustic radiation force, an effect that has been largely overlooked. We also confirm a frequency-dependent topological transition of the acoustic landscape that induces a switching of the field attractors and particle equilibrium points. These results advance the quantitative theory of acoustic forces, unveil previously unresolved dynamical features of acoustofluidic fields, and provide a theoretical foundation for SAW-based cell trapping, separation, and enrichment in acoustofluidics.

physics.flu-dyn↗

arXiv2026

Learning Sparse Compositional Functions with Norm-Constrained Neural Networks

The ability of deep neural networks to learn hierarchical features is widely regarded as a key mechanism underlying their success in high-dimensional learning. Existing theory partially supports this view by establishing approximation rates based on parameter counts and sample complexity guarantees for compositional models without incurring the curse of dimensionality (CoD). To study overparameterized regimes, where the number of parameters exceeds the sample size, we develop a framework that measures complexity via the parameter norm. Within this approach, we establish approximation rates and excess risk bounds for learning sparse compositional functions whose compositional structure is represented by directed acyclic graphs (DAGs), using Frobenius norm-constrained deep neural networks. Our results have broad applicability since every function that is efficiently Turing computable admits sparse compositional representations. In particular, we cover a range of representative models, including multi-index models, binary tree structures, and general compositional architectures. The rates we derive show that deep networks can exploit the compositional structure of the target functions, effectively avoiding the CoD through hierarchical representations.

stat.ML↗

arXiv2026

PromptDx: Differentiable Prompt Tuning for Multimodal In-Context Alzheimer's Diagnosis

Deep learning models in medical imaging typically operate as parametric memory, diagnosing patients by recalling fixed knowledge learned during training. This contrasts sharply with clinical practice, where physicians employ analogical reasoning to diagnose new cases by referencing similar records from past exemplars. While In-Context Learning (ICL) frameworks such as Tabular Prior-Fitted Networks (TabPFN) offer a promising diagnosis-by-reference paradigm, they are designed with tabular-specific inductive priors and rely on non-differentiable preprocessing pipelines, leading to manifold mismatch and gradient fracture when applied to heterogeneous multimodal data. To address these limitations, we propose PromptDx, a novel diagnosis-by-reference framework that leverages a pre-trained TabPFN as an ICL engine while enabling seamless integration with multimodal representations. Our core contribution is a Differentiable Prompt Tuning (DPT) mechanism that aligns a Masked Multimodal Modeling module with the pre-trained ICL engine. By training a lightweight adapter as a differentiable surrogate for the engine's non-differentiable preprocessors, we enable an end-to-end optimization of multimodal prompts within the ICL paradigm. We validate our method on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset using 3D MRI and tabular biomarkers. Experiments demonstrate that our approach outperforms traditional parametric baselines. Notably, our method achieves superior performance using only 1% context samples compared to 30% in standard ICL, demonstrating exceptional manifold condensation ability. We further validate the generalizability of our DPT framework across six tabular datasets with diverse scales. Overall, our method offers a more data-efficient and clinically aligned paradigm for Alzheimer's Disease diagnosis.

cs.CV↗

arXiv2026

Sparse-Aware Neural Networks for Nonlinear Functionals: Mitigating the Exponential Dependence on Dimension

Deep neural networks have emerged as powerful tools for learning operators defined over infinite-dimensional function spaces. However, existing theories frequently encounter difficulties related to dimensionality and limited interpretability. This work investigates how sparsity can help address these challenges in functional learning, a central ingredient in operator learning. We propose a framework that employs convolutional architectures to extract sparse features from a finite number of samples, together with deep fully connected networks to effectively approximate nonlinear functionals. Using universal discretization methods, we show that sparse approximators enable stable recovery from discrete samples. In addition, both the deterministic and the random sampling schemes are sufficient for our analysis. These findings lead to improved approximation rates and reduced sample sizes in various function spaces, including those with fast frequency decay and mixed smoothness. They also provide new theoretical insights into how sparsity can alleviate the curse of dimensionality in functional learning.

cs.LG↗

arXiv2026

TAB-AUDIT: Detecting AI-Fabricated Scientific Tables via Multi-View Likelihood Mismatch

AI-generated fabricated scientific manuscripts raise growing concerns with large-scale breaches of academic integrity. In this work, we present the first systematic study on detecting AI-generated fabricated scientific tables in empirical NLP papers, as information in tables serve as critical evidence for claims. We construct FabTab, the first benchmark dataset of fabricated manuscripts with tables, comprising 1,173 AI-generated papers and 1,215 human-authored ones in empirical NLP. Through a comprehensive analysis, we identify systematic differences between fabricated and real tables and operationalize them into a set of discriminative features within the TAB-AUDIT framework. The key feature, within-table mismatch, captures the perplexity gap between a table's skeleton and its numerical content. Experimental results show that RandomForest built on these features significantly outperform prior state-of-the-art methods, achieving 0.987 AUROC in-domain and 0.883 AUROC out-of-domain. Our findings highlight experimental tables as a critical forensic signal for detecting AI-generated scientific fraud and provide a new benchmark for future research.

cs.CL↗

arXiv2026

Upper limit on HF(1-0) absorption in a dusty star-forming galaxy at $z = 6$: Constraints on early fluorine enrichment

Wolf-Rayet (WR) stars have recently attracted attention as possible drivers of early chemical enrichment, including the production of fluorine, whose nucleosynthetic origin remains debated. To test the contribution of massive stars to fluorine production in the early Universe, we conducted Atacama Large Millimeter/submillimeter Array Band 5 spectroscopy of the HF(1-0) absorption line toward a dusty star-forming galaxy at $z=6.024$. This galaxy has a known gas-phase metallicity and is too young for low-mass AGB stars to have contributed significantly, providing a clean environment to isolate massive-star yields. We do not detect significant HF absorption ($\sim2\sigma$) and derive a conservative 5$\sigma$ upper limit of $N_\mathrm{HF}/N_\mathrm{H_2} < 2.2\times10^{-9}$. This limit is about an order of magnitude below typical local measurements, indicating inefficient fluorine enrichment $\sim0.9$ Gyr after the Big Bang. Comparison with chemical evolution models shows that our constraint is consistent with scenarios without WR yields at this epoch. Expanding the sample of HF absorption measurements in high-redshift galaxies with well-characterized metallicities will be crucial for tracing the onset of WR enrichment and fluorine production across cosmic time.

astro-ph.GA↗

arXiv2025

HunyuanVideo 1.5 Technical Report

We present HunyuanVideo 1.5, a lightweight yet powerful open-source video generation model that achieves state-of-the-art visual quality and motion coherence with only 8.3 billion parameters, enabling efficient inference on consumer-grade GPUs. This achievement is built upon several key components, including meticulous data curation, an advanced DiT architecture featuring selective and sliding tile attention (SSTA), enhanced bilingual understanding through glyph-aware text encoding, progressive pre-training and post-training, and an efficient video super-resolution network. Leveraging these designs, we developed a unified framework capable of high-quality text-to-video and image-to-video generation across multiple durations and resolutions. Extensive experiments demonstrate that this compact and proficient model establishes a new state-of-the-art among open-source video generation models. By releasing the code and model weights, we provide the community with a high-performance foundation that lowers the barrier to video creation and research, making advanced video generation accessible to a broader audience. All open-source assets are publicly available at https://github.com/Tencent-Hunyuan/HunyuanVideo-1.5.

cs.CV↗

arXiv2025

Large gas inflow driven by a matured galactic bar in the early Universe

Bar structures are present in about half of local disk galaxies and play pivotal roles in secular galaxy evolution. Bars impose a non-axisymmetric perturbation to the rotating disk and transport gas inward to feed central starburst and, possibly, the activity of the nuclear supermassive black hole. They are believed to be long-lived structures and are now identified at redshift $z>2$. Yet, little is known about the onset and effect of bars in the early cosmic epoch because spectroscopy of distant bars at sufficient resolution is prohibitively expensive. Here, we report a kinematic study of a galactic bar at redshift 2.467, 2.6 billion years after the Big Bang. We observe the carbon monoxide and atomic carbon emission lines of the dusty star-forming galaxy J0107a and find the bar of J0107a has gas distribution and motion in a pattern identical to local bars. At the same time, the bar drives large-scale non-circular motions that dominate over disk rotation, funneling molecular gas into its center at a rate of $\approx600$ solar masses per year. Our results show that bar-driven dynamical processes and secular evolution were already at play 11.1 billion years ago, powering active star formation amid the gas-rich and far-infrared luminous growth phase in a massive disk galaxy.

astro-ph.GA↗

arXiv2025

Magnetic transition in B2 Al-Cr-Co alloys

Using Density Functional Theory (DFT) calculations and Monte-Carlo (MC) simulations, we investigate the recently reported magnetic transition in B2 Al-Cr-Co alloys. The Cr sublattice is alloyed with different amounts of Co in the antiferromagnetic (AFM) B2 AlCr binary alloy and the resulting exchange interactions are analyzed within the Heisenberg Hamiltonian framework. DFT results reveal that at low Co concentrations the system favors the AFM order, while at high Co contents a transition to the ferromagnetic (FM) state is observed. Within the FM stability field, the Curie temperature (TC), obtained within the mean-field approximation, is below ~160 K and decreases with Co concentration. The calculated exchange parameters evolve systematically with Co content, and the trends are consistent with the DFT total energies. The magnetic configurations obtained from MC simulations follow the DFT results at low Cr levels but predict a spin-glass behavior for alloys containing more than 40 at.% Co on Cr sublattice. These findings provide a fundamental understanding of how the chemistry-driven changes in exchange interactions affect magnetism in the B2 Al-Cr-Co alloys.

cond-mat.mtrl-sci↗

arXiv2025

Learning Multi-Index Models with Hyper-Kernel Ridge Regression

Deep neural networks excel in high-dimensional problems, outperforming models such as kernel methods, which suffer from the curse of dimensionality. However, the theoretical foundations of this success remain poorly understood. We follow the idea that the compositional structure of the learning task is the key factor determining when deep networks outperform other approaches. Taking a step towards formalizing this idea, we consider a simple compositional model, namely the multi-index model (MIM). In this context, we introduce and study hyper-kernel ridge regression (HKRR), an approach blending neural networks and kernel methods. Our main contribution is a sample complexity result demonstrating that HKRR can adaptively learn MIM, overcoming the curse of dimensionality. Further, we exploit the kernel nature of the estimator to develop ad hoc optimization approaches. Indeed, we contrast alternating minimization and alternating gradient methods both theoretically and numerically. These numerical results complement and reinforce our theoretical findings.

stat.ML↗

arXiv2025

Zero-Shot Privacy-Aware Text Rewriting via Iterative Tree Search

The increasing adoption of large language models (LLMs) in cloud-based services has raised significant privacy concerns, as user inputs may inadvertently expose sensitive information. Existing text anonymization and de-identification techniques, such as rule-based redaction and scrubbing, often struggle to balance privacy preservation with text naturalness and utility. In this work, we propose a zero-shot, tree-search-based iterative sentence rewriting algorithm that systematically obfuscates or deletes private information while preserving coherence, relevance, and naturalness. Our method incrementally rewrites privacy-sensitive segments through a structured search guided by a reward model, enabling dynamic exploration of the rewriting space. Experiments on privacy-sensitive datasets show that our approach significantly outperforms existing baselines, achieving a superior balance between privacy protection and utility preservation.

cs.CL↗