arXiv subjects

Zhiqiang Sheng

Publications and source records attributed to Zhiqiang Sheng.

8 recordsLinked to original sources

arXiv2026

InEdit-Bench: Benchmarking Intermediate Logical Pathways for Intelligent Image Editing Models

Multimodal generative models have made significant strides in image editing, demonstrating impressive performance on a variety of static tasks. However, their proficiency typically does not extend to complex scenarios requiring dynamic reasoning, leaving them ill-equipped to model the coherent, intermediate logical pathways that constitute a multi-step evolution from an initial state to a final one. This capacity is crucial for unlocking a deeper level of procedural and causal understanding in visual manipulation. To systematically measure this critical limitation, we introduce InEdit-Bench, the first evaluation benchmark dedicated to reasoning over intermediate pathways in image editing. InEdit-Bench comprises meticulously annotated test cases covering four fundamental task categories: state transition, dynamic process, temporal sequence, and scientific simulation. Additionally, to enable fine-grained evaluation, we propose a set of assessment criteria to evaluate the logical coherence and visual naturalness of the generated pathways, as well as the model's fidelity to specified path constraints. Our comprehensive evaluation of 14 representative image editing models on InEdit-Bench reveals significant and widespread shortcomings in this domain. By providing a standardized and challenging benchmark, we aim for InEdit-Bench to catalyze research and steer development towards more dynamic, reason-aware, and intelligent multimodal generative models.

cs.CV↗

arXiv2026

Subspace method based on neural networks for eigenvalue problems

In this paper, we propose a subspace method based on neural networks for eigenvalue problems with high accuracy and low cost. We first construct a neural network-based orthogonal basis by some deep learning method and dimensionality reduction technique, and then calculate the Galerkin projection of the eigenvalue problem onto the subspace spanned by the orthogonal basis and obtain an approximate solution. Numerical experiments show that we can obtain approximate eigenvalues and eigenfunctions with very high accuracy but low cost.

math.NA↗

arXiv2025

Bridging the Gap: Enhancing Gaze-Performance Link in Children with ASD through Dual-Level Visual Guidance in MR-DMT

Autism Spectrum Disorder (ASD) is marked by action imitation deficits stemming from visuomotor integration impairments, posing challenges to imitation-based learning, such as dance movement therapy in mixed reality (MR-DMT). Previous gaze-guiding interventions in ASD have mainly focused on optimizing gaze in isolation, neglecting the crucial "gaze-performance link". This study investigates enhancing this link in MR-DMT for children with ASD. Initially, we experimentally confirmed the weak link: longer gaze durations didn't translate to better performance. Then, we proposed and validated a novel dual-level visual guidance system that operates on both perceptual and transformational levels: not only directing attention to task-relevant areas but also explicitly scaffolding the translation from gaze perception to performance execution. Our results demonstrate its effectiveness in boosting the gaze-performance link, laying key foundations for more precisely tailored and effective MR-DMT interventions for ASD.

cs.HC↗

arXiv2025

Domain Decomposition Subspace Neural Network Method for Solving Linear and Nonlinear Partial Differential Equations

This paper proposes a domain decomposition subspace neural network method for efficiently solving linear and nonlinear partial differential equations. By combining the principles of domain decomposition and subspace neural networks, the method constructs basis functions using neural networks to approximate PDE solutions. It imposes $C^k$ continuity conditions at the interface of subdomains, ensuring smoothness across the global solution. Nonlinear PDEs are solved using Picard and Newton iterations, analogous to classical methods. Numerical experiments demonstrate that our method achieves exceptionally high accuracy, with errors reaching up to $10^{-13}$, while significantly reducing computational costs compared to existing approaches, including PINNs, DGM, DRM. The results highlight the method's superior accuracy and training efficiency.

math.NA↗

arXiv2025

Alternately-optimized SNN method for acoustic scattering problem in unbounded domain

In this paper, we propose a novel machine learning-based method to solve the acoustic scattering problem in unbounded domain. We first employ the Dirichlet-to-Neumann (DtN) operator to truncate the physically unbounded domain into a computable bounded domain. This transformation reduces the original scattering problem in the unbounded domain to a boundary value problem within the bounded domain. To solve this boundary value problem, we design a neural network with a subspace layer, where each neuron in this layer represents a basis function. Consequently, the approximate solution can be expressed by a linear combination of these basis functions. Furthermore, we introduce an innovative alternating optimization technique which alternately updates the basis functions and their linear combination coefficients respectively by training and least squares methods. In our method, we set the coefficients of basis functions to 1 and use a new loss function each time train the subspace. These innovations ensure that the subspace formed by these basis functions is truly optimized. We refer to this method as the alternately-optimized subspace method based on neural networks (AO-SNN). Extensive numerical experiments demonstrate that our new method can significantly reduce the relative $l^2$ error to $10^{-7}$ or lower, outperforming existing machine learning-based methods to the best of our knowledge.

math.NA↗

arXiv2024

Improved randomized neural network methods with boundary processing for solving elliptic equations

We present two improved randomized neural network methods, namely RNN-Scaling and RNN-Boundary-Processing (RNN-BP) methods, for solving elliptic equations such as the Poisson equation and the biharmonic equation. The RNN-Scaling method modifies the optimization objective by increasing the weight of boundary equations, resulting in a more accurate approximation. We propose the boundary processing techniques on the rectangular domain that enforce the RNN method to satisfy the non-homogeneous Dirichlet and clamped boundary conditions exactly. We further prove that the RNN-BP method is exact for some solutions with specific forms and validate it numerically. Numerical experiments demonstrate that the RNN-BP method is the most accurate among the three methods, the error is reduced by 6 orders of magnitude for some tests.

math.NA↗

arXiv2024

Subspace method based on neural networks for solving the partial differential equation in weak form

We present a subspace method based on neural networks for solving the partial differential equation in weak form with high accuracy. The basic idea of our method is to use some functions based on neural networks as base functions to span a subspace, then find an approximate solution in this subspace. Training base functions and finding an approximate solution can be separated, that is different methods can be used to train these base functions, and different methods can also be used to find an approximate solution. In this paper, we find an approximate solution of the partial differential equation in the weak form. Our method can achieve high accuracy with low cost of training. Numerical examples show that the cost of training these base functions is low, and only one hundred to two thousand epochs are needed for most tests. The error of our method can fall below the level of $10^{-7}$ for some tests. The proposed method has the better performance in terms of the accuracy and computational cost.

math.NA↗

arXiv2024

Subspace method based on neural networks for solving the partial differential equation

We present a subspace method based on neural networks (SNN) for solving the partial differential equation with high accuracy. The basic idea of our method is to use some functions based on neural networks as base functions to span a subspace, then find an approximate solution in this subspace. We design two special algorithms in the strong form of partial differential equation. One algorithm enforces the equation and initial boundary conditions to hold on some collocation points, and another algorithm enforces $L^2$-norm of the residual of the equation and initial boundary conditions to be $0$. Our method can achieve high accuracy with low cost of training. Moreover, our method is free of parameters that need to be artificially adjusted. Numerical examples show that the cost of training these base functions of subspace is low, and only one hundred to two thousand epochs are needed for most tests. The error of our method can even fall below the level of $10^{-10}$ for some tests. The performance of our method significantly surpasses the performance of PINN and DGM in terms of the accuracy and computational cost.

math.NA↗