arXiv subjects

Nan Zhang

Publications and source records attributed to Nan Zhang.

At least 19 recordsLinked to original sources

arXiv2026

Super bound states in the continuum: Classification, direct computation, and geometry in parameter space

In periodic structures, resonant states near a bound state in the continuum (BIC) have quality ($Q$) factors scaling as $Q\sim 1/δ^{2μ}$, where $δ$ is the wavevector detuning from the BIC. While generic BICs have $μ=1$, super-BICs with $μ\geq 2$ give rise to higher-$Q$ resonances over a broad wavevector range, making them attractive for enhancing light-matter interactions. Here, we develop a systematic theoretical and computational framework for studying super-BICs. We first classify them according to $μ$ and symmetry. We then study their unfolding under structural variations, characterizing the bifurcations of nearby generic BICs and determining the minimum number $n$ of additional tunable structural parameters required to recover a super-BIC of the same class. We devise a direct computational method for locating super-BICs together with their associated structural parameters and efficiently tracing their families. Finally, we investigate the local geometry of the BIC set in the product space of structural parameters and the Brillouin zone. This geometric framework provides a unified interpretation of the unfolding of super-BICs and offers a new understanding of BIC merging and splitting phenomena. Our results establish a theoretical and computational foundation for the systematic study of super-BICs, with potential applications in resonant optics and photonic device design.

physics.optics↗

arXiv2026

Topological Leading Angular Structure around Bound States in the Continuum

We show that the angular structure of the leading radiation around a bound state in the continuum (BIC) directly encodes its topology. This angular information can be determined from the BIC itself and used to design prescribed topological polarization textures. As examples, we identify BICs carrying high topological charges $q=4$ and $q=-5$ in $C_{6v}$ photonic crystal slabs, addressing the question of whether high-charge BICs exist and how they can be systematically realized. We further show that zeros of the leading radiation can drive both topological transitions and the bifurcation of new BIC families. These findings may enable new approaches to polarization engineering in structured light and resonant photonics.

physics.optics↗

arXiv2026

The sparse regularity method for graphs with few even-cycle homomorphisms

Let $C_k$ denote a cycle on $k$ vertices. Pascadi (2026) established a removal lemma for $C_{2k+1}$ in graphs with few $C_{2k}$-homomorphisms under a dense-pairs condition, using Schatten--von Neumann norms and entropy methods. We give a short proof of a version with more restrictive partition and diagonal requirements, extending the combinatorial approach of Conlon, Fox, Sudakov and Zhao (2021) without using Pascadi's Schatten-norm regularity framework. We illustrate the method with a known sparse removal statement for odd product equations in finite groups.

math.CO↗

arXiv2026

An auditable conditional-strategy framework for open-ended decision-making in complex lung cancer

Complex lung cancer decisions can involve several defensible pathways whose eligibility, sequencing and safety depend on unresolved information. Effective support must make explicit how patient conditions govern pathway eligibility, deferral and redirection. MedGPT Clinical Explorer (MCE) organizes alternatives, decision-changing unknowns, safety constraints and fallback into a conditional strategy for clinician review. To evaluate this representation in physician-authored strategies, multidisciplinary experts established case-specific references for 40 cases within a purposive 100-case corpus, and 250 physicians from 98 institutions produced 2,250 strategies under unaided, retrieval-reference and MCE-assisted conditions. MCE-assisted strategies expressed more applicable clinical requirements, measured by the Admissible Pathway Attainment Score (APAS; 0-100), than unaided strategies (adjusted difference, 12.87; 95% CI, 11.18-14.55) and retrieval-reference strategies (5.22; 3.52-6.93). With the same knowledge base available in the retrieval-reference and MCE-assisted conditions, the additional content centered on candidate pathways, decision-critical information and safety constraints. Physicians' whole-strategy acceptability judgments correlated with APAS (Spearman's rho = 0.671), while a complementary relationship audit assessed whether candidates, conditions and subsequent actions were coherently connected. Together, these findings identify two complementary dimensions of open-ended decision support: coverage of clinically relevant content and coherent links among pathways, conditions and subsequent actions. MCE provides a shared decision object that makes consequential omissions and pathway contingencies visible before action; prospective studies should evaluate its effects on clinical workflow and patient outcomes.

cs.AI↗

arXiv2026

SweepANN: A GPU-Accelerated Large-K Approximate Vector Search for Drug Discovery

DrugCLIP places small molecules and protein pockets in one space, turning genome-wide drug discovery into large-K retrieval by vector proximity. A campaign fixes over 20K pockets in advance for one library of over 500M molecules. Each pocket keeps K = 500K candidates, 0.1% of the collection, versus 100 in ANN benchmarks. Missed hits never get tested, so mean recall must reach 99% relative to exact search. Large answers make IVF probe every list holding a result and graph search track K or more candidates, so costs grow with K. On our CPUs and GPUs, neither index family reaches the target without losing most of its edge over scanning. SweepANN partitions compressed vectors across GPUs and scans each resident partition. One matrix multiplication scores each block for a whole query batch, reading it once. Several plans perform the K-dependent selection and merging of each query's K answers, each returning an exact top-K under compressed scoring. The window plan retains each query's best K from sampled blocks as its seed, and only rows above each seed's minimum score, shared once across GPUs, enter the buffers. Four Blackwell GPUs (RTX PRO 6000) answer all 26,562 pockets with a resident time of about 61 seconds, excluding library loading, and 99.6% mean recall relative to exact FP32 search. DrugCLIP reports roughly 24 hours with eight A100 GPUs in its own campaign. On 500M rows, the window plan runs 1.41x faster than SweepANN's grouped plan in the same memory. Across 25M-500M rows and K of 10K-500K, all GPU IVF configurations meeting the recall target take 8.2-24x SweepANN's resident time. On DEEP1B's 1B vectors across eight GPUs, against SweepANN's exact full-score scan of uncompressed FP32 rows, the window plan cuts resident time by 5.4x and 3.2x at K = 100K and 500K. It also cuts per-GPU peak memory by 6.0x and 5.3x, losing 1.0 and 0.7 mean-recall points.

cs.DB↗

arXiv2026

The START mission: Probing the 2029 Apophis Flyby via a Low-Cost Geocentric SmallSat

The Student-led Threatening Asteroid Reconnaissance of Tsinghua (START) marks the inaugural mission of the Tianxing Program, a deep-space exploration initiative led by students at Tsinghua University. Conceived as a low-cost, rapid-response small-satellite mission, START will investigate the near-Earth asteroid (99942) Apophis during its close approach to Earth in April 2029, when significant terrestrial tidal forces will offer a rare opportunity to observe the physical and dynamical response of a rubble-pile asteroid in real time. The 300 kg spacecraft is scheduled for rideshare launch into low Earth orbit in early 2028 and will then use solar electric propulsion to transfer to a circular mission orbit with a semimajor axis of approximately 38,000 km and an inclination of 55 degrees. START will execute a high-speed flyby of Apophis from a closest distance of 7 km at the asteroid's closest approach to Earth, to capture its tidal response. The payload suite consists of a high-resolution narrow-field camera, a wide-field navigation camera, and three near-infrared multispectral imagers. By acquiring centimeter-scale imagery and meter-scale reflectance spectra, the mission will characterize the asteroid's surface morphology and composition and monitor immediate tidally induced surface modifications. Ultimately, START will provide geometrically complementary, high-cadence datasets to international flagship missions to Apophis, demonstrating a highly scalable and cost-effective architecture for future planetary defense and small-body exploration.

astro-ph.EP↗

arXiv2026

On the Nonasymptotic Scaling Guarantee of Hyperparameter Estimation in Inhomogeneous, Weakly-Dependent Complex Network Dynamical Systems

Hierarchical Bayesian models are increasingly used in large, inhomogeneous complex network dynamical systems by modeling parameters as draws from a hyperparameter-governed distribution. However, theoretical guarantees for these estimates as the network population size grows have been lacking. A critical concern is that hyperparameter estimation may diverge for larger networks, undermining the model's reliability. Formulating the system's evolution in a measure transport perspective, we propose a theoretical framework for estimating hyperparameters with mean-type observations, which are prevalent in many scientific applications. Our primary contribution is a nonasymptotic bound for the deviation of estimate of hyperparameters in inhomogeneous complex network dynamical systems with respect to network population size, which is established for a general family of optimization algorithms within a fixed observation duration. For systems with independent nodes, we first establish a fixed-accuracy probabilistic hyperparameter bound and then use it to derive an explicit nonasymptotic hyperparameter bound. We subsequently extend both bounds to the more challenging and practically relevant setting of systems with weakly-dependent nodes. We validate our theoretical findings with numerical experiments on two representative models: a Susceptible-Infected-Susceptible model and a Spiking Neuronal Network model. In both cases, the results confirm that the estimation error decreases as the network population size increases, aligning with our theoretical guarantees. This research proposes the foundational theory to ensure that hierarchical Bayesian methods are statistically consistent for large-scale inhomogeneous systems, filling a gap in this area of theoretical research and justifying their application in practice.

math.ST↗

arXiv2026

An extreme ram-pressure stripping event in a protocluster at redshift 4.3

In the nearby Universe, the environment plays a crucial role in suppressing star formation in dense regions. In particular, ram-pressure stripping (RPS) is a major mechanism for removing gas from galaxies in clusters, occurring when galaxies travel through a dense hot atmosphere and leave trailing gaseous wakes. By depleting the cold gas reservoir, RPS can drive outside-in quenching and is therefore thought to be an important route for transforming cluster galaxies. At earlier times, however, the hot atmosphere in protoclusters is expected to be immature, so environmental effects are commonly assumed to be dominated by gravitational interactions. Here we report ALMA and JWST observations of SPT2349$-$56-C26 (hereafter C26), a massive galaxy experiencing an extreme RPS event in the SPT2349$-$56 protocluster at $z\,{=}\,4.3$. More than half of the [CII]-traced cold gas lies outside its stellar body, with the emission peak offset by 6 kpc. These observations show that RPS can remove most of the cold gas from massive galaxies in dense protocluster cores as early as $z\,{=}\,4.3$, providing a direct hydrodynamic pathway for environmental quenching at $z\,{>}\,4$.

astro-ph.GA↗

arXiv2026

Fourier modal method for perturbation analysis of bound states in the continuum

Bound states in the continuum (BICs) supported by periodic photonic structures are surrounded by high-$Q$ resonances and serve as centers of polarization vortices in momentum space, making them attractive for a wide range of applications. Recently, a perturbation theory has been formulated for resonant states near BICs, yielding a hierarchy of equations whose solutions directly approximate the resonant states and determine the asymptotic behavior of their $Q$ factors and polarizations. Efficiently solving these equations is therefore essential. Since many studies of BICs concern layered structures, we develop an approach based on the Fourier modal method. Numerical examples confirm the effectiveness of the proposed method and demonstrate its ability to capture higher-order asymptotic scaling. Our work provides a practical tool for the theoretical analysis of BICs and may also facilitate the design of BIC-based photonic devices.

physics.optics↗

arXiv2026

Online Learning of Functional Principal Component Analysis for Multidimensional Functional Data

Multidimensional functional data streams arise in diverse scientific fields, yet their analysis poses significant challenges. We propose a novel online framework for functional principal component analysis that enables efficient and scalable modeling of such data. Our method represents functional principal components using tensor product splines, enforcing smoothness and orthonormality through a penalized framework on a Stiefel manifold. We develop an efficient Riemannian stochastic gradient descent algorithm and a Riemannian adaptive gradient (AdaGrad) variant, both utilizing iterative averaging techniques to stabilize the estimation and accelerate convergence. Additionally, a dynamic tuning strategy for smoothing parameter selection is developed based on a rolling averaged block validation score that adapts to the streaming nature of the data. Furthermore, we derive the asymptotic normality of the estimators and construct pointwise confidence intervals to quantify the uncertainty of the estimated functional principal components. Extensive simulations and real-world applications demonstrate the flexibility and effectiveness of this framework for analyzing multidimensional functional data.

stat.ME↗

arXiv2026

Why Do Reasoning Models Lose Coverage? The Role of Data and Forks in the Road

Recent progress in large language models has led to the emergence of reasoning models, which have shown strong performance on complex tasks through specialized fine-tuning procedures. While these methods reliably improve pass@1 accuracy, prior works have observed that they show a coverage shrinkage behavior, where pass@k degrades relative to the base model. In this paper, we investigate the cause of reasoning shrinkage under SFT-based post-training. We hypothesize that this behavior is driven by properties of the fine-tuning data, specifically related to decision points or "forks in the road" scenarios where model encounters indecipherable patterns with multiple valid reasoning paths. To test this hypothesis, we design controlled case studies that simulate such decision-point settings, spanning indecipherable nodes in graph branching, and reasoning modes. By tracking post-training dynamics in these settings, we find that the shrinkage phenomenon is tightly correlated with the prevalence of decision-point scenarios in the training data. We also demonstrate that this shrinkage behavior can be partially mitigated through targeted data synthesis design of decision-points and a more systematic diversity-encouraging decoding mechanism. Our findings identify data-centric factors as a key driver of shrinkage in reasoning models and highlight diversity-aware designs as an effective lever for controlling it. (Data and code for reproducing our experiments are available at https://github.com/psunlpgroup/reasoning_forks )

cs.LG↗

arXiv2026

Quantifying the Causal Operational Determinants of Service Reliability in Urban Rail Transit: Evidence from Panel Double/Debiased Machine Learning

Urban rail transit reliability is a critical measure of system performance, yet its causal determinants remain poorly quantified due to high-dimensional and interdependent influencing factors. This study investigates reliability patterns across 46 international metro operators between 1994 and 2024 using the CoMET benchmarking database, incorporating more than 90 candidate variables spanning technical, operational, financial, environmental, and macroeconomic conditions. Based on domain knowledge, literature synthesis, and variable construction, four operational determinants are designed to capture three mechanisms: demand pressure, service supply, and demand-supply imbalance, while the remaining variables are screened and incorporated as confounders where theoretically appropriate. Double/Debiased Machine Learning (DML) adapted for panel data is introduced to urban rail reliability analysis to quantify the net causal effects of these determinants under complex and nonlinear relationships. The framework combines flexible machine learning with panel fixed or random effects within-operator temporal variation, reducing bias from high-dimensional confounding, model misspecification, and unobserved operator heterogeneity. The results identify three distinct operational mechanisms. Higher passenger demand intensity increases incident rates by 0.38% (p<0.001). On the supply side, greater fleet supply adequacy and car-based operational intensity reduce incident rates by 0.52% (p<0.05) and 0.80% (p<0.01), respectively. Capacity utilization, which reflects the imbalance between demand and available supply, increases incident rates by 0.49% (p<0.001). These findings show that metro reliability depends not only on the level of demand or supply alone, but also on whether service provision keeps pace with passenger demand.

stat.AP↗

arXiv2026

A Unified Description of Electron-Phonon Coupling and Ion Migration in Metal Halide Perovskites

The remarkable optoelectronic properties of metal halide perovskites are closely linked to their unusually soft and polar chemical bonds that enable both strong electron-phonon interactions and ion migration. Yet these two defining characteristics have largely been treated as independent consequences of the same underlying chemical bonding. Here we show that they originate from a common electronic-structure framework by developing a general description linking lattice dynamics, electron-phonon coupling, and halide ion migration across representative Pb-based, Sn-based, and double perovskites. Spectrally resolved phonon-mode contributions demonstrate that the low-frequency shearing modes dominate halide migration, whereas high-frequency stretching modes govern carrier scattering through the Fröhlich interaction in all three compositions. We introduce an orbital hybridization descriptor to unify these findings, which connects metal-halide bonding characteristics with the migration barrier energies and Fröhlich coupling strengths, indicating a cooperative evolution of these two properties. These findings provide a generalized microscopic mechanism for simultaneously optimizing charge and ionic transport in soft semiconductors.

cond-mat.mtrl-sci↗

arXiv2026

Triton for MTIA: Bridging the Programming Model Gaps for Custom AI Accelerators

The rapid growth in machine learning workloads has fueled the proliferation of custom accelerator architectures. Designed from the ground up, these accelerators often expose programming models that are distinct from GPUs. While hyperscalers and AI chip startups continue to innovate in this space, achieving broad operator coverage to support diverse models remains a major challenge. Additionally, an easy-to-use, high-level kernel programming language is important for rapid iteration of models and kernels. Triton, together with TorchInductor, addresses these issues on GPUs, but its viability on accelerators with different programming models has yet to be established. In this work, we present the first production-scale application of Triton on a custom ML accelerator, MTIA-2i, developed by Meta. To support MTIA-2i, we develop a new compiler backend that targets it, introduce enhancements to TorchInductor code generation, and propose minimal language extensions that expose MTIA-specific architectural features. We demonstrate that Triton-MTIA kernels achieve performance competitive with expert-tuned C++ implementations. Leveraging these development efficiency gains, we successfully deployed manually written and Inductor-generated Triton kernels in production across approximately 60 different model types, accounting for 50% of layers and 47% of non-GEMM execution time for these models. Our results provide compelling evidence that DSLs like Triton can bridge the programming model gaps between ML frameworks, kernels, and custom accelerators, enabling rapid innovation and efficient deployment at scale.

cs.PL↗

arXiv2026

Amplitude analysis for charmed meson decays at BESIII

Amplitude analysis bridges the gap between experimental measurements of multibody charmed-meson decays and theoretical predictions of intermediate two-body processes. This work presents a comprehensive overview of the amplitude-analysis methodology employed by the BESIII Collaboration, emphasizing practical implementation. We detail the construction of the probability density function and likelihood function for unbinned maximum-likelihood fits. This encompasses Monte Carlo integration techniques for normalization, the incorporation of detection efficiency and resolution effects, and multidimensional background modeling utilizing XGBoost classifiers. Furthermore, we describe the amplitude formalism for both hadronic and semileptonic decays, incorporating standard resonance-propagator parametrizations. Key analytical aspects, including the evaluation of fit fractions, the generation of kinematic projections, and the estimation of statistical uncertainties, are also discussed.

hep-ex↗

arXiv2026

DocPure: Prompt-Free Unified Document Restoration via Degradation-Aware Structure-Guided Wavelet Modulation

High-quality document images are pivotal for information archiving and downstream automatic processing. However, they are frequently compromised by diverse degradations during uncontrolled acquisition and transmission. While unified document restoration techniques have been proposed to restore images from multiple degradations, they often struggle with training multiple degradation-specific models, reliance on manual task-specific prompts, or cross-task data pairing. To address these limitations, we propose DocPure, a prompt-free unified framework that achieves degradation-aware document restoration. We design a degradation-aware structure auto-encoder with degradation-informed routing regularization to predict clean structural priors from degraded inputs. The model is prompt-free at inference, and degradation labels are only used as auxiliary supervision for the routing regularization during training. Furthermore, we introduce a structure-guided wavelet interaction mechanism to bridge frequency-domain features and spatial semantics. Within the structure-guided wavelet interaction mechanism, a cross-frequency adaptive modulation utilizes low-frequency sub-bands to modulate high-frequency recovery, ensuring structural consistency. Extensive experiments demonstrate that DocPure achieves strong performance compared with state-of-the-art methods across various tasks, including deblurring, denoising, compression artifact reduction, and deshadowing.

cs.CV↗

arXiv2026

ToolSciVer: Multimodal Scientific Claim Verification with Visual Tool Augmented Reinforcement Learning

Multimodal Scientific Claim Verification (MSCV) requires models to verify scientific claims using visually grounded evidence from papers, including figures, tables, charts, and textual context. However, existing methods often fail because they struggle to locate decisive visual evidence, accurately read structured scientific visuals, and integrate multimodal observations into reliable reasoning. We introduce ToolSciVer, the first tool-augmented framework for MSCV to our knowledge. ToolSciVer equips a VLM with three type-aware visual tools, table row/column focus, chart-to-structure parsing, and high-resolution region zoom, which convert dense scientific visuals into explicit, claim-facing evidence, and trains the policy with Group Relative Policy Optimization (GRPO) under a composite reward of answer correctness, format validity, length control, tool-use efficiency, and tool-validity penalties. Experiments on SciVer and MuSciClaims datasets on five VLMs from three model families (Qwen, InternVL, Gemma) demonstrate that our method achieves superior performance compared to four competitive baselines including prompting-based and RL-based tool-use methods, highlighting the effectiveness of learned, type-aware tool use for scientific claim verification.

cs.CL↗

arXiv2026

Scene Graph Thinking: Reinforcing Structured Visual Reasoning for Multimodal Large Language Models

Multimodal Large Language Models (MLLMs) have demonstrated strong perception and reasoning capabilities. However, most existing models focus on isolated objects and neglect structured relationships for efficient target navigation, limiting their performance on visually intensive tasks. To address this challenge, we introduce Scene Graph Thinking (SaGe), a novel paradigm that enables fine-grained and structured visual reasoning through explicit scene-graph representations. Specifically, we first introduce an automated data engine that converts flat image-text corpora into structured scene graphs, where hierarchical entities constitute the nodes and diverse visual relations define the edges. Building upon this, we construct 120K high-quality training data by sampling reasoning traces from scene graphs. Then, two-stage graph-aligned post-training paradigms are introduced, where supervised fine-tuning internalizes MLLMs with structured reasoning, and subsequent reinforcement fine-tuning proposes node-as-proxy graph rewards to consolidate efficient graph exploration. With curated data and graph-aligned training, our approach achieves significant improvements across eight multimodal benchmarks, demonstrating strong effectiveness on fine-grained perception and reasoning tasks. Code is available at https://github.com/zwyang6/SaGe.

cs.CV↗