arXiv subjects

Yanlong Zhang

Publications and source records attributed to Yanlong Zhang.

4 recordsLinked to original sources

arXiv2026

EntSQL: A Benchmark for Grounding Text-to-SQL in Long-Context Enterprise Knowledge

Text-to-SQL enables natural language access to databases, and recent LLMs have substantially advanced its capabilities. Existing benchmarks such as Spider, BIRD, and Spider~2.0 evaluate schema generalization, large-scale databases, and realistic workflows, but largely overlook enterprise scenarios where SQL generation depends on private business knowledge, such as internal metrics, reporting conventions, and organizational rules. We introduce EntSQL, an enterprise-oriented Text-to-SQL benchmark for evaluating long-context grounding over proprietary business documents. EntSQL contains 1,066 aligned Chinese-English semantic examples across five business domains, with most examples requiring domain knowledge beyond the question and schema and involving complex SQL structures. On English inputs, the best evaluated system reaches only 15.9\% when long-form documents are provided, highlighting the difficulty of grounding SQL generation in enterprise knowledge.

cs.CL↗

arXiv2026

A fourth-order area-preserving curve flow in centro-equiaffine geometry

In this paper, inspired by the work of Guan and Li (2015), we introduce a fourth-order centro-equiaffine invariant curve flow via the affine Minkowski formula. Without any smallness assumptions on the initial curve, we establish the long-time existence of the flow and prove that, as $t \to +\infty$, the evolving curve preserves its enclosed area and converges smoothly to a round circle up to the action of $\mathrm{SL}(2)$.

math.DG↗

arXiv2026

BSoNet: Deep Learning Solution for Optimizing Image Quality of Portable Backscatter Imaging Systems

Portable backscatter imaging systems (PBI) integrate an X-ray source and detector in a single unit, utilizing Compton scattering photons to rapidly acquire superficial or shallow structural information of an inspected object through single-sided imaging. The application of this technology overcomes the limitations of traditional transmission X-ray detection, offering greater flexibility and portability, making it the preferred tool for the rapid and accurate identification of potential threats in scenarios such as borders, ports, and industrial nondestructive security inspections. However, the image quality is significantly compromised due to the limited number of Compton backscattered photons. The insufficient photon counts result primarily from photon absorption in materials, the pencil-beam scanning design, and short signal sampling times. It therefore yields severe image noise and an extremely low signal-to-noise ratio, greatly reducing the accuracy and reliability of PBI systems. To address these challenges, this paper introduces BSoNet, a novel deep learning-based approach specifically designed to optimize the image quality of PBI systems. The approach significantly enhances image clarity, recognition, and contrast while meeting practical application requirements. It transforms PBI systems into more effective and reliable inspection tools, contributing significantly to strengthening security protection.

eess.IV↗

arXiv2024

On length-preserving and area-preserving inverse curvature flow of planar curves with singularities

This paper aims to investigate the evolution problem for planar curves with singularities. Motivated by the inverse curvature flow introduced by Li and Wang (Calc. Var. Partial Differ. Equ. 62 (2023), No. 135), we intend to consider the area-preserving and length-preserving inverse curvature flow with nonlocal term for $\ell$-convex Legendre curves. For the area-preserving flow, an $\ell$-convex Legendre curve %of with initial algebraic area $A_0>0$ evolves to a circle of radius $\sqrt{\frac{A_0}{\pi}}$. For the length-preserving flow, an $\ell$-convex Legendre curve %of with initial algebraic length $L_0$ evolves to a circle of radius $\frac{L_0}{2\pi}$. As the by-product, we obtain some geometric inequalities for $\ell$-convex Legendre curves through the length-preserving flow.

math.DG↗