arXiv subjects

Jinlong He

Publications and source records attributed to Jinlong He.

10 recordsLinked to original sources

arXiv2026

RAFM: Retrieval-Augmented Flow Matching for Unpaired CBCT-to-CT Translation

Cone-beam CT (CBCT) is routinely acquired in radiotherapy but suffers from severe artifacts and unreliable Hounsfield Unit (HU) values, limiting its direct use for dose calculation. Synthetic CT (sCT) generation from CBCT is therefore an important task, yet paired CBCT--CT data are often unavailable or unreliable due to temporal gaps, anatomical variation, and registration errors. In this work, we introduce rectified flow (RF) into unpaired CBCT-to-CT translation in medical imaging. Although RF is theoretically compatible with unpaired learning through distribution-level coupling and deterministic transport, its practical effectiveness under small medical datasets and limited batch sizes remains underexplored. Direct application with random or batch-local pseudo pairing can produce unstable supervision due to semantically mismatched endpoint samples. To address this challenge, we propose Retrieval-Augmented Flow Matching (RAFM), which adapts RF to the medical setting by constructing retrieval-guided pseudo pairs using a frozen DINOv3 encoder and a global CT memory bank. This strategy improves empirical coupling quality and stabilizes unpaired flow-based training. Experiments on SynthRAD2023 under a strict subject-level true-unpaired protocol show that RAFM outperforms existing methods across FID, MAE, SSIM, PSNR, and SegScore. The code is available at https://github.com/HiLab-git/RAFM.git.

cs.CV↗

arXiv2026

FuncDroid: Towards Inter-Functional Flows for Comprehensive Mobile App GUI Testing

As mobile application (app) functionalities grow increasingly complex and their iterations accelerate, ensuring high reliability presents significant challenges. While functionality-oriented GUI testing has attracted growing research attention, existing approaches largely overlook interactions across functionalities, making them ineffective at uncovering deep bugs hidden in inter-functional behaviors. To fill this gap, we first design a Functional Flow Graph (FFG), a behavioral model that explicitly captures an app's functional units and their inter-functional interactions. Based on the FFG, we further introduce an inter-functional-flow-oriented GUI testing approach with the dual goals of precise model construction and deep bug detection. This approach is realized through a long-short-term-view-guided testing process. By combining two complementary test-generation views, it can adaptively refine functional boundaries and systematically explore inter-functional flows under diverse triggering conditions. We implement our approach in a tool called FuncDroid, and evaluate it on two benchmarks: (1) a widely-used open-source benchmark with 50 reproducible crash bugs and (2) a diverse set of 52 popular commercial apps. Experimental results demonstrate that FuncDroid significantly outperforms state-of-the-art baselines in both coverage (+28%) and bug detection number (+107%). Moreover, FuncDroid successfully uncovers 18 previously unknown non-crash functional bugs in commercial apps, confirming its practical effectiveness.

cs.SE↗

arXiv2025

DINOv3-Guided Cross Fusion Framework for Semantic-aware CT generation from MRI and CBCT

Generating synthetic CT images from CBCT or MRI has a potential for efficient radiation dose planning and adaptive radiotherapy. However, existing CNN-based models lack global semantic understanding, while Transformers often overfit small medical datasets due to high model capacity and weak inductive bias. To address these limitations, we propose a DINOv3-Guided Cross Fusion (DGCF) framework that integrates a frozen self-supervised DINOv3 Transformer with a trainable CNN encoder-decoder. It hierarchically fuses global representation of Transformer and local features of CNN via a learnable cross fusion module, achieving balanced local appearance and contextual representation. Furthermore, we introduce a Multi-Level DINOv3 Perceptual (MLDP) loss that encourages semantic similarity between synthetic CT and the ground truth in DINOv3's feature space. Experiments on the SynthRAD2023 pelvic dataset demonstrate that DGCF achieved state-of-the-art performance in terms of MS-SSIM, PSNR and segmentation-based metrics on both MRI$\rightarrow$CT and CBCT$\rightarrow$CT translation tasks. To the best of our knowledge, this is the first work to employ DINOv3 representations for medical image translation, highlighting the potential of self-supervised Transformer guidance for semantic-aware CT synthesis. The code is available at https://github.com/HiLab-git/DGCF.

cs.CV↗

arXiv2025

HACMony: Automatically Detecting Hopping-related Audio-stream Conflict Issues on HarmonyOS

HarmonyOS is emerging as a popular distributed operating system for diverse mobile devices. One of its standout features is app-hopping, which allows users to seamlessly transition apps across different HarmonyOS devices. However, when apps playing audio streams hop between devices, they can easily trigger Hopping-related Audio-stream Conflict (HAC) scenarios. Improper resolution of HAC will lead to significant HAC issues, which are harder to detect compared to single-device audio-stream conflicts, due to the unclear semantics of HarmonyOS's app-hopping mechanism and the lack of effective multi-app hopping testing methods. To fill the gap, this paper introduces an automated and efficient approach to detecting HAC issues. We formalized the operational semantics of HarmonyOS's app-hopping mechanism for audio streams for the first time. Leveraging this formalization, we designed an Audio Service Transition Graph (ASTG) to model the behaviors of audio-API-related services and proposed a model-based approach to detect HAC issues automatically. Our techniques were implemented in a tool, HACMony, and evaluated on 20 real-world HarmonyOS apps. Experimental results reveal that 11 of the 20 apps exhibit HAC issues. Additionally, we summarized the detected issues into two typical types, namely MoD and MoR, and analyzed their characteristics to assist and guide both app and OS developers.

cs.SE↗

arXiv2025

PeFoMed: Parameter Efficient Fine-tuning of Multimodal Large Language Models for Medical Imaging

Multimodal large language models (MLLMs) represent an evolutionary expansion in the capabilities of traditional large language models, enabling them to tackle challenges that surpass the scope of purely text-based applications. It leverages the knowledge previously encoded within these language models, thereby enhancing their applicability and functionality in the reign of multimodal contexts. Recent works investigate the adaptation of MLLMs as a universal solution to address medical multi-modal problems as a generative task. In this paper, we propose a parameter efficient framework for fine-tuning MLLMs, specifically validated on medical visual question answering (Med-VQA) and medical report generation (MRG) tasks, using public benchmark datasets. We also introduce an evaluation metric using the 5-point Likert scale and its weighted average value to measure the quality of the generated reports for MRG tasks, where the scale ratings are labelled by both humans manually and the GPT-4 model. We further assess the consistency of performance metrics across traditional measures, GPT-4, and human ratings for both VQA and MRG tasks. The results indicate that semantic similarity assessments using GPT-4 align closely with human annotators and provide greater stability, yet they reveal a discrepancy when compared to conventional lexical similarity measurements. This questions the reliability of lexical similarity metrics for evaluating the performance of generative models in Med-VQA and report generation tasks. Besides, our fine-tuned model significantly outperforms GPT-4v. This indicates that without additional fine-tuning, multi-modal models like GPT-4v do not perform effectively on medical imaging tasks. The code will be available here: https://github.com/jinlHe/PeFoMed.

cs.CL↗

arXiv2024

Parameter-Efficient Fine-Tuning Medical Multimodal Large Language Models for Medical Visual Grounding

Multimodal Large Language Models (MLLMs) inherit the superior text understanding capabilities of LLMs and extend these capabilities to multimodal scenarios. These models achieve excellent results in the general domain of multimodal tasks. However, in the medical domain, the substantial training costs and the requirement for extensive medical data pose challenges to the development of medical MLLMs. Furthermore, due to the free-text form of answers, tasks such as visual grounding that need to produce output in a prescribed form become difficult for MLLMs. So far, there have been no medical MLLMs works in medical visual grounding area. For the medical vision grounding task, which involves identifying locations in medical images based on short text descriptions, we propose Parameter-efficient Fine-tuning medical multimodal large language models for Medcial Visual Grounding (PFMVG). To validate the performance of the model, we evaluate it on a public benchmark dataset for medical visual grounding, where it achieves competitive results, and significantly outperforming GPT-4v. Our code will be open sourced after peer review.

cs.CV↗

arXiv2023

Masked Vision and Language Pre-training with Unimodal and Multimodal Contrastive Losses for Medical Visual Question Answering

Medical visual question answering (VQA) is a challenging task that requires answering clinical questions of a given medical image, by taking consider of both visual and language information. However, due to the small scale of training data for medical VQA, pre-training fine-tuning paradigms have been a commonly used solution to improve model generalization performance. In this paper, we present a novel self-supervised approach that learns unimodal and multimodal feature representations of input images and text using medical image caption datasets, by leveraging both unimodal and multimodal contrastive losses, along with masked language modeling and image text matching as pretraining objectives. The pre-trained model is then transferred to downstream medical VQA tasks. The proposed approach achieves state-of-the-art (SOTA) performance on three publicly available medical VQA datasets with significant accuracy improvements of 2.2%, 14.7%, and 1.7% respectively. Besides, we conduct a comprehensive analysis to validate the effectiveness of different components of the approach and study different pre-training settings. Our codes and models are available at https://github.com/pengfeiliHEU/MUMC.

cs.CV↗

arXiv2020

High-Temperature Ultra-Broad UV-MIR High-Efficiency Absorber Based on Double Ring-Shaped Titanium Nitride Resonators

An ultrabroad absorber based on double-ring-shaped titanium nitride (TiN) nanoresonators, which can work in high temperatures, is proposed and numerically studied. The absorber with some optimal parameters exhibits an averaged absorption of 94.6% in the range of 200 - 4000 nm (from ultraviolet to mid-infrared) and a band from 200 - 3518 nm having an absorption > 90%. We have demonstrated in detail the physical mechanisms of the ultra-broad absorption, including the dielectric lossy property of TiN material itself in shorter wavelengths and plasmonic resonances caused by the metallic property of TiN nano-resonators in longer wavelengths. In addition, the absorber shows polarization independent and wide-angle acceptance. Another absorber with double TiN nano-rings of different heights has flatter and higher absorption efficiency (more than 95% absorption) at 200-2860 nm waveband. These properties make the proposed absorbers based on TiN has great potentials in many applications, such as light trapping, photovoltaics, thermal emitters.

physics.optics↗

arXiv2020

Enhancing single photon emission through quasi-bound states in the continuum of monolithic hexagonal boron nitride metasurface

A patterned structure of monolithic hexagonal boron nitride (hBN) on a glass substrate, which can enhance the emission of the embedded single photon emitters (SPEs), is useful for onchip single-photon sources of high-quality. Here, we design and demonstrate a monolithic hBN metasurface with quasi-bound states in the continuum mode at emission wavelength with ultrahigh Q values to enhance fluorescence emission of SPEs in hBN. Because of ultrahigh electric field enhancement inside the proposed hBN metasurface, an ultrahigh Purcell factor (3.3*10^4) is achieved. In addition, the Purcell factor can also be strongly enhanced in most part of the hBN structure, which makes the hBN metasurface suitable for e.g. monolithic quantum photonics.

physics.optics↗

arXiv2020

A Decision Procedure for Path Feasibility of String Manipulating Programs with Integer Data Type

Strings are widely used in programs, especially in web applications. Integer data type occurs naturally in string-manipulating programs, and is frequently used to refer to lengths of, or positions in, strings. Analysis and testing of string-manipulating programs can be formulated as the path feasibility problem: given a symbolic execution path, does there exist an assignment to the inputs that yields a concrete execution that realizes this path? Such a problem can naturally be reformulated as a string constraint solving problem. Although state-of-the-art string constraint solvers usually provide support for both string and integer data types, they mainly resort to heuristics without completeness guarantees. In this paper, we propose a decision procedure for a class of string-manipulating programs which includes not only a wide range of string operations such as concatenation, replaceAll, reverse, and finite transducers, but also those involving the integer data-type such as length, indexof, and substring. To the best of our knowledge, this represents one of the most expressive string constraint languages that is currently known to be decidable. Our decision procedure is based on a variant of cost register automata. We implement the decision procedure, giving rise to a new solver OSTRICH+. We evaluate the performance of OSTRICH+ on a wide range of existing and new benchmarks. The experimental results show that OSTRICH+ is the first string decision procedure capable of tackling finite transducers and integer constraints, whilst its overall performance is comparable with the state-of-the-art string constraint solvers.

cs.LO↗