arXiv subjects

Junlong Ma

Publications and source records attributed to Junlong Ma.

4 recordsLinked to original sources

arXiv2026

Thermal and Microstructural Simulations of Photonic Sintering of Oxide Ceramics: A Two-Scale Scheme

Photonic sintering (PS) offers an ultra-fast, contact-free alternative to conventional sintering and has demonstrated its potential for enhancing the sinterability of acceptor-doped barium zirconate (BZY) ceramics. However, a central challenge in the PS process lies in achieving precise control over thermal self-stabilization in the presence of complex microstructural effects arising from photonic-ray--induced thermal profiles. To elucidate the interplay among thermal fields, microstructural evolution, and PS process parameters, this study establishes a two-scale, non-isothermal simulation framework. The framework integrates macroscopic heat-transfer simulations, incorporating effective heat conduction and photonic-ray--induced volumetric heating in the porous media, with microscopic non-isothermal phase-field sintering simulations that resolve microstructure evolution under local thermal profile. Scale bridging is achieved through a temperature field transferring and mapping that satisfies Hill-Mandel condition between the macroscopic and microscopic simulations, while maintaining synchronization between their asynchronous time-stepping schemes. After calibrating model parameters against experimental measurements, the framework successfully reproduces the experimentally observed porosity inhomogeneity along the sample depth. The influence of enhanced localized mass transport is further examined through a parametric investigation of surface and grain boundary diffusivities. Overall, the proposed framework demonstrates its feasibility and physical interpretability in establishing process-microstructure relationships for the scalable fabrication of high-performance protonic ceramics.

cond-mat.mtrl-sci↗

arXiv2024

Enhanced Control for Diffusion Bridge in Image Restoration

Image restoration refers to the process of restoring a damaged low-quality image back to its corresponding high-quality image. Typically, we use convolutional neural networks to directly learn the mapping from low-quality images to high-quality images achieving image restoration. Recently, a special type of diffusion bridge model has achieved more advanced results in image restoration. It can transform the direct mapping from low-quality to high-quality images into a diffusion process, restoring low-quality images through a reverse process. However, the current diffusion bridge restoration models do not emphasize the idea of conditional control, which may affect performance. This paper introduces the ECDB model enhancing the control of the diffusion bridge with low-quality images as conditions. Moreover, in response to the characteristic of diffusion models having low denoising level at larger values of \(\bm t \), we also propose a Conditional Fusion Schedule, which more effectively handles the conditional feature information of various modules. Experimental results prove that the ECDB model has achieved state-of-the-art results in many image restoration tasks, including deraining, inpainting and super-resolution. Code is avaliable at https://github.com/Hammour-steak/ECDB.

eess.IV↗

arXiv2023

Image Restoration Through Generalized Ornstein-Uhlenbeck Bridge

Diffusion models exhibit powerful generative capabilities enabling noise mapping to data via reverse stochastic differential equations. However, in image restoration, the focus is on the mapping relationship from low-quality to high-quality images. Regarding this issue, we introduce the Generalized Ornstein-Uhlenbeck Bridge (GOUB) model. By leveraging the natural mean-reverting property of the generalized OU process and further eliminating the variance of its steady-state distribution through the Doob's h-transform, we achieve diffusion mappings from point to point enabling the recovery of high-quality images from low-quality ones. Moreover, we unravel the fundamental mathematical essence shared by various bridge models, all of which are special instances of GOUB and empirically demonstrate the optimality of our proposed models. Additionally, we present the corresponding Mean-ODE model adept at capturing both pixel-level details and structural perceptions. Experimental outcomes showcase the state-of-the-art performance achieved by both models across diverse tasks, including inpainting, deraining, and super-resolution. Code is available at \url{https://github.com/Hammour-steak/GOUB}.

cs.CV↗

arXiv2021

Context-guided Triple Matching for Multiple Choice Question Answering

The task of multiple choice question answering (MCQA) refers to identifying a suitable answer from multiple candidates, by estimating the matching score among the triple of the passage, question and answer. Despite the general research interest in this regard, existing methods decouple the process into several pair-wise or dual matching steps, that limited the ability of assessing cases with multiple evidence sentences. To alleviate this issue, this paper introduces a novel Context-guided Triple Matching algorithm, which is achieved by integrating a Triple Matching (TM) module and a Contrastive Regularization (CR). The former is designed to enumerate one component from the triple as the background context, and estimate its semantic matching with the other two. Additionally, the contrastive term is further proposed to capture the dissimilarity between the correct answer and distractive ones. We validate the proposed algorithm on several benchmarking MCQA datasets, which exhibits competitive performances against state-of-the-arts.

cs.CL↗