arXiv subjects

Yuqing Liu

Publications and source records attributed to Yuqing Liu.

At least 19 recordsLinked to original sources

arXiv2026

Parameter Bounds and Inverse Approximation for Linearized ReLU$^k$ Networks on the Sphere

We study direct and inverse approximation for linearized shallow ReLU$^k$ networks on $\mathbb S^d$ with quasi-uniform hidden parameters. For $0<α<\frac{d+2k+1}{2d}$, under the coefficient growth condition $\bigl(n\sum_{j=1}^na_{j,n}^2\bigr)^{\frac{1}{2}}\leq n^αM$, we prove that approximation at the order $n^{-\frac{d+2k+1}{2d}+α}$ is equivalent to membership in the parity-compatible Besov space $\mathcal B_{2,\infty,*}^{\frac{d+2k+1}{2}-αd}(\mathbb S^d)$. Mere convergence under the same coefficient budget does not imply this regularity. For unconstrained approximation along a nested parameter sequence, a single ridge function gives a counterexample when $α<\frac{1}{2}$, whereas for $α>\frac{1}{2}$ the endpoint Besov inverse conclusion follows from a Bernstein inequality under antipodal quasi-uniformity. The inverse conclusion is also recovered when the prescribed rate holds for two quasi-uniform parameter sequences whose union is antipodally separated.

math.NA↗

arXiv2026

Rethinking Semantic ID Construction for Generative Recommendation: SimHash with Parallel Decoding and Semantic Alignment

Semantic ID-based generative recommendation represents each item as a sequence of discrete tokens, enabling structured modeling of item semantics. A critical challenge is constructing semantic IDs that are both semantically expressive and computationally efficient. While recent approaches favor complex learned quantization, simple hashing-based methods such as SimHash are widely regarded as fundamentally inferior. In this work, we challenge this consensus by showing that the apparent performance gap does not stem from inherent limitations of hashing, but rather from a structural mismatch with autoregressive decoding, coupled with the inevitable information loss during rigid discretization. Based on this insight, we propose FLASH, a two-stage framework that revitalizes training-free SimHash tokenization through parallel decoding and explicit semantic alignment. Despite its simplicity, FLASH achieves state-of-the-art performance across multiple datasets without requiring any tokenizer training, while exhibiting stronger generalization in cold-start scenarios. Notably, we demonstrate that semantic alignment acts as a universally effective mechanism across diverse paradigms. Our findings suggest that, with compatible decoding and semantic grounding, simple and efficient tokenizers can achieve performance comparable to complex learned counterparts in generative recommendation. Our code is available at https://github.com/KevinC2015/Flash.

cs.IR↗

arXiv2026

LLMAdBench: A Human Preference Benchmark for Advertising in LLM Responses

Inserting advertisements (ads) into consumer-facing LLM output is emerging as a new business model, but there is little shared evidence on how such ad insertion should be evaluated or how it affects user preferences. We introduce LLMAdBench, a human-preference benchmark for studying advertising in LLM-generated content. The benchmark isolates a simple but practically important decision: given a user conversation, an LLM response, and a matched advertisement, where should the ad be placed? Our dataset compares pairs of responses that differ only in ad position while holding all other conditions fixed including the user query, base answer, advertisement, and disclosure condition. Human annotators evaluate each pair based on six criteria from both advertiser's and user's perspectives. The resulting benchmark contains more than 18000 human judgments across two disclosure conditions: explicitly labeling the ad as sponsored and merging it into the response without disclosure. We use LLMAdBench to evaluate eight frontier LLMs as preference judges and find that they are not reliable substitutes for human evaluation. Even the most stable models reverse roughly one quarter of their decisions when the presentation order is swapped, agreement across models is low, and their placement preferences differ systematically from those of human annotators. Moreover, LLMAdBench contains substantial learnable signal. In particular, a Qwen3-8B model fine-tuned on the human preferences improves substantially over its base model and outperforms all zero-shot frontier judges on the held-out prediction task. Beyond model evaluation, LLMAdBench provides quantitative evidence on the advertiser-user trade-off and shows that the sponsorship disclosure systematically changes users' preference over ad placement.

cs.AI↗

arXiv2026

Exploring the Temporal Consistency for Point-Level Weakly-Supervised Temporal Action Localization

Point-supervised Temporal Action Localization (PTAL) adopts a lightly frame-annotated paradigm (\textit{i.e.}, labeling only a single frame per action instance) to train a model to effectively locate action instances within untrimmed videos. Most existing approaches design the task head of models with only a point-supervised snippet-level classification, without explicit modeling of understanding temporal relationships among frames of an action. However, understanding the temporal relationships of frames is crucial because it can help a model understand how an action is defined and therefore benefits localizing the full frames of an action. To this end, in this paper, we design a multi-task learning framework that fully utilizes point supervision to boost the model's temporal understanding capability for action localization. Specifically, we design three self-supervised temporal understanding tasks: (i) Action Completion, (ii) Action Order Understanding, and (iii) Action Regularity Understanding. These tasks help a model understand the temporal consistency of actions across videos. To the best of our knowledge, this is the first attempt to explicitly explore temporal consistency for point supervision action localization. Extensive experimental results on four benchmark datasets demonstrate the effectiveness of the proposed method compared to several state-of-the-art approaches.

cs.CV↗

arXiv2026

Boosting Point-supervised Temporal Action Localization via Text Refinement and Alignment

Recently, point-supervised temporal action localization has gained significant attention for its effective balance between labeling costs and localization accuracy. However, current methods primarily rely on visual features and do not fully exploit the complementary semantic information contained in textual descriptions. To address this issue, we propose a Text Refinement and Alignment (TRA) framework that incorporates refined textual semantics to complement visual representations for point-supervised temporal action localization. This is achieved by designing two new modules for the original point-supervised framework: a Point-based Text Refinement module (PTR) and a Point-based Multimodal Alignment module (PMA). Specifically, we first generate descriptions for video frames using a pre-trained multimodal model. Next, PTR refines the initial descriptions by leveraging point annotations together with multiple fixed pre-trained models. PMA then projects the visual and textual features into a unified semantic space and employs a point-based multimodal contrastive learning objective to reduce the gap between visual and linguistic modalities. Finally, the aligned multimodal features are fed into the action detector for temporal action localization. Extensive experiments on five widely used benchmarks demonstrate that TRA consistently improves strong point-supervised baselines and achieves competitive performance compared with state-of-the-art methods. In particular, on THUMOS'14, TRA achieves 58.5% AVG mAP@[0.1:0.7], outperforming the visual-only baseline by 2.3%.

cs.CV↗

arXiv2026

Tunable Mid-Infrared Chiral Selective Absorber Based on Asymmetric V-Shaped Metasurfaces Driven by Chiral quasi-Bound State in the Continum

Efficient discrimination of circularly polarized light (CPL) is of great significance in photonics. In this study, we propose a nanophotonic device based on asymmetric V-shaped metasurfaces that exhibits strong discrimination between left- and right-circularly polarized (LCP and RCP) light at the resonant wavelengths of the absorption spectra. The chiral-selective response originates from a quasi-bound state in the continuum (qBIC) mode enabled by controlled symmetry breaking in the V-shaped structure, which exhibits high absorption under LCP illumination while the resonance is strongly suppressed under RCP incidence, leading to a large absorption contrast between the two circular polarizations. This significant absorption difference enables highly efficient chiral discrimination. Furthermore, the resonant wavelength can be broadly tuned from 5200 to 6200 nm by scaling the structural dimensions without compromising the high absorption contrast between LCP and RCP. This work not only enables high-performance chiral detection and separation, but also offers valuable guidance for reconfigurable chiral nanodevices, with promising applications in areas such as enantiomer sensing, chiral imaging, and CPL spectroscopy.

physics.optics↗

arXiv2026

Metasurface-based Terahertz Three-dimensional Holography Enabled by Physics-Informed Neural Network

Artificial intelligence has revolutionized optical device design, overcoming the efficiency bottlenecks of traditional methods. For holographic metasurfaces, conventional iterative algorithms suffer from time-consuming iterations and convergence stagnation, especially as the complexity of 3D target fields increases. While recent deep-learning-based algorithms have improved the trade-off between speed and image quality, most existing models remain constrained by predefined physical scenarios (e.g., fixed distances), limiting their adaptability in dynamic practical applications. To address these challenges, we propose a physics-informed neural network (PINN) based on local polynomial fitting and multi-plane wave propagation (LM-PINN) for the rapid design of terahertz 3D holographic metasurfaces. By leveraging a self-supervised training strategy, LM-PINN eliminates the need for labeled datasets, enabling direct end-to-end mapping from target holographic patterns to the metasurface structures. Both simulated and experimental results demonstrate that LM-PINN-designed metasurfaces offer higher imaging quality than traditional iterative algorithms. Crucially, by incorporating a distance encoding process, a single trained LM-PINN generalizes effectively across diverse physical configurations, including varying diffraction distances and distinct 2D or 3D targets, eliminating the necessity for retraining. Furthermore, the inference process of LM-PINN typically takes less than 1 second, providing a multifold speed advantage over traditional algorithms. Consequently, this strategy offers a robust and universal framework that paves the way for high-quality, real-time, and large-scale 3D holographic technologies.

physics.optics↗

arXiv2026

Multi-LLM Query Optimization

Deploying multiple large language models (LLMs) in parallel to classify an unknown ground-truth label is a common practice, yet the problem of optimally allocating queries across heterogeneous models remains poorly understood. In this paper, we formulate a robust, offline query-planning problem that minimizes total query cost subject to statewise error constraints which guarantee reliability for every possible ground-truth label. We first establish that this problem is NP-hard via a reduction from the minimum-weight set cover problem. To overcome this intractability, we develop a surrogate by combining a union bound decomposition of the multi-class error into pairwise comparisons with Chernoff-type concentration bounds. The resulting surrogate admits a closed-form, multiplicatively separable expression in the query counts and is guaranteed to be feasibility-preserving. We further show that the surrogate is asymptotically tight at the optimization level: the ratio of surrogate-optimal cost to true optimal cost converges to one as error tolerances shrink, with an explicit rate of $O\left(\log\log(1/α_{\min}) / \log(1/α_{\min})\right)$. Finally, we design an asymptotic fully polynomial-time approximation scheme (AFPTAS) that returns a surrogate-feasible query plan within a $(1+\varepsilon)$ factor of the surrogate optimum.

cs.DS↗

arXiv2026

Fourier Transform Infrared microspectroscopy-based super-resolution virtual staining of unlabeled tissues by pixel Diffusion Transformer

Here, we present a diffusion transformer (DiT)-based pixel super-resolution virtual staining approach to transform low-resolution FTIR microspectroscopic images of the unstained tissues into corresponding high-resolution H&E-stained images. Unlike conventional conditional DiT architectures, this method models the transformation from FTIR images to H&E-stained images as a stochastic Brownian bridge process and directly learns the cross-domain translation in pixel space by means of a large-patch Transformer. When applied to FTIR images of unlabeled human lung tissue samples, the proposed method successfully transforms them into high-resolution H&E-stained images, achieving a 4 times pixel-level super-resolution. Additionally, by partitioning images into large patches, our method achieves a fourfold improvement in inference speed compared with traditional U-Net-based diffusion models, without compromising the quality of generated images. This super-resolution virtual staining method provides a rapid and effective solution for generating high-resolution, clinically usable H&E-stained images from infrared spectroscopic images, which can significantly facilitate the incorporation of FTIR microspectroscopy into clinical histological scenarios.

physics.optics↗

arXiv2026

Estimating the Containment Effectiveness and Economic Cost of Inner-city Non-Pharmaceutical Interventions

Non-pharmaceutical interventions (NPIs) are crucial for controlling pandemics, but existing research often overlooks the heterogeneity of individual behavior, which can lead to inaccurate evaluations of the effectiveness of strategies. In this paper, we use a large dataset of fine-grained real-world individual trajectory data from a major Chinese city to examine the trade-off between the epidemic containment effectiveness and economic cost of different NPIs. Our findings reveal significant variations in the outcomes of different NPIs across activation mechanisms and initial scales of undetected transmission. Based on these results, we construct a two-dimensional evaluation framework that comprehensively evaluates the impact of both the containment effectiveness and economic cost, which suggests that implementing stringent strategies-such as lockdown or contact tracing-at low activation thresholds can achieve optimal epidemic control with minimal economic cost. Our study provides a data-driven decision-making framework for understanding the implementation effectiveness and applicability of emergency management policies within urban systems.

physics.soc-ph↗

arXiv2026

Partitionable Diffractive Neural Networks for Multifunctional Optical Operations

Diffractive neural network (DNN), which can perform machine learning tasks based on the light propagation and diffraction, has recently emerged as a promising optical computing paradigm due to its high parallel processing speed and low power consumption nature. However, existing diffractive network architectures face challenges in implementing functional reconfiguration. Once a diffractive neural network is fabricated, its functionality is fixed. Deploying such systems for different tasks typically requires reconstructing the entire physical setup, which significantly compromises hardware efficiency in practical applications. In this work, we propose the multifunctional partitionable diffractive neural networks (PDNNs) that can generate networks with additional capabilities by stacking multiple sub-modules with independent functions in the horizontal direction. Each submodule functions as an independent diffractive network capable of performing specific imaging or classification tasks. When these submodules are combined, they can form a new network with additional functionalities. Moreover, assembling these submodules in different configurations enables structures with diverse functions. This powerful PDNN framework demonstrates remarkable advantages in flexibility and reconfigurability for multitask operations, opening a new pathway for realizing multifunctional and integrated optical artificial intelligence systems.

physics.optics↗

arXiv2025

Adaptive Candidate Retrieval with Dynamic Knowledge Graph Construction for Cold-Start Recommendation

The cold-start problem remains a critical challenge in real-world recommender systems, as new items with limited interaction data or insufficient information are frequently introduced. Despite recent advances leveraging external knowledge such as knowledge graphs (KGs) and large language models (LLMs), recommender systems still face challenges in practical environments. Static KGs are expensive to construct and quickly become outdated, while LLM-based methods depend on pre-filtered candidate lists due to limited context windows. To address these limitations, we propose ColdRAG, a retrieval-augmented framework that dynamically constructs a knowledge graph from raw metadata, extracts entities and relations to construct an updatable structure, and introduces LLM-guided multi-hop reasoning at inference time to retrieve and rank candidates without relying on pre-filtered lists. Experiments across multiple benchmarks show that ColdRAG consistently outperforms strong seven baselines.

cs.IR↗

arXiv2025

LLMInit: A Free Lunch from Large Language Models for Selective Initialization of Recommendation

Collaborative filtering (CF) is widely adopted in industrial recommender systems (RecSys) for modeling user-item interactions across numerous applications, but often struggles with cold-start and data-sparse scenarios. Recent advancements in pre-trained large language models (LLMs) with rich semantic knowledge, offer promising solutions to these challenges. However, deploying LLMs at scale is hindered by their significant computational demands and latency. In this paper, we propose a novel and scalable LLM-RecSys framework, LLMInit, designed to integrate pretrained LLM embeddings into CF models through selective initialization strategies. Specifically, we identify the embedding collapse issue observed when CF models scale and match the large embedding sizes in LLMs and avoid the problem by introducing efficient sampling methods, including, random, uniform, and variance-based selections. Comprehensive experiments conducted on multiple real-world datasets demonstrate that LLMInit significantly improves recommendation performance while maintaining low computational costs, offering a practical and scalable solution for industrial applications. To facilitate industry adoption and promote future research, we provide open-source access to our implementation at https://github.com/DavidZWZ/LLMInit.

cs.IR↗

arXiv2025

How Close Are We? Limitations and Progress of AI Models in Banff Lesion Scoring

The Banff Classification provides the global standard for evaluating renal transplant biopsies, yet its semi-quantitative nature, complex criteria, and inter-observer variability present significant challenges for computational replication. In this study, we explore the feasibility of approximating Banff lesion scores using existing deep learning models through a modular, rule-based framework. We decompose each Banff indicator - such as glomerulitis (g), peritubular capillaritis (ptc), and intimal arteritis (v) - into its constituent structural and inflammatory components, and assess whether current segmentation and detection tools can support their computation. Model outputs are mapped to Banff scores using heuristic rules aligned with expert guidelines, and evaluated against expert-annotated ground truths. Our findings highlight both partial successes and critical failure modes, including structural omission, hallucination, and detection ambiguity. Even when final scores match expert annotations, inconsistencies in intermediate representations often undermine interpretability. These results reveal the limitations of current AI pipelines in replicating computational expert-level grading, and emphasize the importance of modular evaluation and computational Banff grading standard in guiding future model development for transplant pathology.

cs.CV↗

arXiv2025

ME-FIRST: A Metasurface-Enhanced Fingerprint InfraRed Spectroscopic Tool for Fluid Analytes

Infrared (IR) spectroscopy has emerged as a pivotal tool in biomedical diagnostics, offering label-free spectral biomarkers for the detection of numerous diseases, particularly in the fingerprint region. However, the lack of rapid and sensitive IR spectroscopic techniques for analyzing complex fluid analytes remains a critical challenge in clinical practice. To address this limitation, we present a Metasurface-Enhanced Fingerprint InfraRed Spectroscopic Tool (ME-FIRST) that enhances light-matter interactions in sub-wavelength volumes through plasmonic resonances across the entire fingerprint range from $1900 cm^{-1}$ to $1000 cm^{-1}$. Numerical simulations reveal confined and enhanced electric near-field, with an average probing depth of ~100 nm and enhancement factor $|E/E_0|$ of ~60-fold at resonant peaks. The ME-FIRST device is further experimentally fabricated and validated, and as a proof of concept, we demonstrate the sensing of molecular vibrational modes with a considerable sensitivity in L-lysine over the full fingerprint IR spectral range. The proposed ME-FIRST presents a promising platform for high-sensitivity IR spectroscopy of fluid analytes, paving the way for clinical applications of infrared spectroscopy in biofluid analysis and pathological scenarios.

physics.optics↗

arXiv2025

Theory of periodic convolutional neural network

We introduce a novel convolutional neural network architecture, termed the \emph{periodic CNN}, which incorporates periodic boundary conditions into the convolutional layers. Our main theoretical contribution is a rigorous approximation theorem: periodic CNNs can approximate ridge functions depending on $d-1$ linear variables in a $d$-dimensional input space, while such approximation is impossible in lower-dimensional ridge settings ($d-2$ or fewer variables). This result establishes a sharp characterization of the expressive power of periodic CNNs. Beyond the theory, our findings suggest that periodic CNNs are particularly well-suited for problems where data naturally admits a ridge-like structure of high intrinsic dimension, such as image analysis on wrapped domains, physics-informed learning, and materials science. The work thus both expands the mathematical foundation of CNN approximation theory and highlights a class of architectures with surprising and practically relevant approximation capabilities.

cs.LG↗

arXiv2025

Generalization Analysis for Classification on Korobov Space

In this paper, the classification algorithm arising from Tikhonov regularization is discussed. The main intention is to derive learning rates for the excess misclassification error according to the convex $η$-norm loss function $ϕ(v)=(1 - v)_{+}^η$, $η\geq1$. Following the argument, the estimation of error under Tsybakov noise conditions is studied. In addition, we propose the rate of $L_p$ approximation of functions from Korobov space $X^{2, p}([-1,1]^{d})$, $1\leq p \leq \infty$, by the shallow ReLU neural network. This result consists of a novel Fourier analysis

math.ST↗

arXiv2025

High mechanical strength Si anode synthesis with interlayer bonded expanded graphite structure for lithium-ion batteries

Despite advancements in silicon-based anodes for high-capacity lithium-ion batteries, their widespread commercial adoption is still hindered by significant volume expansion during cycling, especially at high active mass loadings crucial for practical use. The root of these challenges lies in the mechanical instability of the material, which subsequently leads to the structural failure of the electrode. Here, we present a novel synthesis of a composite combining expanded graphite and silicon nanoparticles. This composite features a unique interlayer-bonded graphite structure, achieved through the application of a modified spark plasma sintering method. Notably, this innovative structure not only facilitates efficient ion and electron transport but also provides exceptional mechanical strength (Vickers hardness: up to 658 MPa, Young's modulus: 11.6 GPa). This strength effectively accommodates silicon expansion, resulting in an impressive areal capacity of 2.9 mA h cm-2 (736 mA h g-1) and a steady cycle life (93% after 100 cycles). Such outstanding performance is paired with features appropriate for large-scale industrial production of silicon batteries, such as active mass loading of at least 3.9 mg cm-2, a high-tap density electrode material of 1.68 g cm-3 (secondary clusters: 1.12 g cm-3), and a production yield of up to 1 kg per day.

cond-mat.mtrl-sci↗