Author name cluster

Mengyu Li

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

7 papers

1 author row

EAAI Journal 2026 Journal Article

A multi-modal multi-task learning network for intelligent parameter measurement in gas–liquid two-phase flow

Hanqing Chen
Zhiqiang Zhao
Bang Zhou
Ruiqi Wang
Mengyu Li
Wei Li
Jun Liu
Weidong Cao

Accurate identification of flow patterns and reliable measurement of phase fraction are fundamental for monitoring and control in gas–liquid two-phase flow systems. Conventional sensing and modeling approaches, however, are often constrained by limited spatial resolution and adaptability to dynamic operating conditions. A multi-modal multi-task learning network (MMLNet) is proposed, which integrates spatially distributed conductance time-series signals acquired from a custom-designed sensor with synchronized high-speed flow images. The network adopts a dual-branch architecture, where modality-specific backbones are constructed using multi-scale depthwise separable convolutions, followed by attention-driven cross-modal interaction and a per-token sample gate for adaptive fusion. Under a unified multi-task objective, MMLNet jointly optimizes flow pattern classification and gas volume fraction (GVF) regression, thereby exploiting the inherent correlation between the two tasks to improve accuracy and generalization. Experimental results show that MMLNet achieves 99. 88% accuracy in flow pattern classification, with a mean absolute error (MAE) of 0. 63%, and a mean absolute percentage error (MAPE) of 2. 23% for GVF prediction, outperforming state-of-the-art baselines. These results highlight the potential of MMLNet as a scalable soft-sensing solution for multiphase flow monitoring.

Details DOI

AAAI Conference 2025 Conference Paper

Boosting Short Text Classification with Multi-Source Information Exploration and Dual-Level Contrastive Learning

Yonghao Liu
Mengyu Li
Wei Pang
Fausto Giunchiglia
Lan Huang
Xiaoyue Feng
Renchu Guan

Short text classification, as a research subtopic in natural language processing, is more challenging due to its semantic sparsity and insufficient labeled samples in practical scenarios. We propose a novel model named MI-DELIGHT for short text classification in this work. Specifically, it first performs multi-source information (i.e., statistical information, linguistic information, and factual information) exploration to alleviate the sparsity issues. Then, the graph learning approach is adopted to learn the representation of short texts, which are presented in graph forms. Moreover, we introduce a dual-level (i.e., instance-level and cluster-level) contrastive learning auxiliary task to effectively capture different-grained contrastive information within massive unlabeled data. Meanwhile, previous models merely perform the main task and auxiliary tasks in parallel, without considering the relationship among tasks. Therefore, we introduce a hierarchical architecture to explicitly model the correlations between tasks. We conduct extensive experiments across various benchmark datasets, demonstrating that MI-DELIGHT significantly surpasses previous competitive models. It even outperforms popular large language models on several datasets.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Gaussian Herding across Pens: An Optimal Transport Perspective on Global Gaussian Reduction for 3DGS

Tao Wang
Mengyu Li
Geduo Zeng
Cheng Meng
Qiong Zhang

3D Gaussian Splatting (3DGS) has emerged as a powerful technique for radiance field rendering, but it typically requires millions of redundant Gaussian primitives, overwhelming memory and rendering budgets. Existing compaction approaches address this by pruning Gaussians based on heuristic importance scores, without global fidelity guarantee. To bridge this gap, we propose a novel optimal transport perspective that casts 3DGS compaction as global Gaussian mixture reduction. Specifically, we first minimize the composite transport divergence over a KD-tree partition to produce a compact geometric representation, and then decouple appearance from geometry by fine-tuning color and opacity attributes with far fewer Gaussian primitives. Experiments on benchmark datasets show that our method (i) yields negligible loss in rendering quality (PSNR, SSIM, LPIPS) compared to vanilla 3DGS with only 10\% Gaussians; and (ii) consistently outperforms state-of-the-art 3DGS compaction techniques. Notably, our method is applicable to any stage of vanilla or accelerated 3DGS pipelines, providing an efficient and agnostic pathway to lightweight neural rendering.

PDF Details

YNICL Journal 2025 Journal Article

Region-based U-nets for fast, accurate, and scalable deep brain segmentation: Application to Parkinson Plus Syndromes

Mengyu Li
Magnús Magnússon
Ingibjörg Kristjánsdóttir
Sigrún Helga Lund
Thilo van Eimeren
Lotta M. Ellingsen

The early diagnosis of age-related neurodegenerative diseases, which often progress to dementia, poses significant clinical challenges due to subtle and overlapping symptoms of these diseases at early stage. Automated MRI segmentation is important for early detection, as it offers consistent measurements and the ability to detect subtle structural changes in the brain. Manual segmentation is impractical for large datasets or clinical use. Deep learning approaches provide fast processing, however, they often encounter graphics processing unit (GPU) memory constraints when handling large datasets. Here we introduce a deep learning-based approach using region-based U-nets specifically designed to segment 12 deep-brain structures relevant to Parkinson Plus Syndromes. By dividing the brain image into targeted regions around the brainstem, ventricular system, and striatum, our method optimizes GPU usage and significantly reduces training times, while maintaining high accuracy. Validating the proposed method on three datasets, including a 660-subject clinical dataset comprising both healthy controls and patients with various movement disorders, we demonstrate robustness and practical applicability in separating different diseases. The method achieves superior segmentation performance compared to state-of-the-art methods, with a mean Dice Similarity Coefficient (DSC) of 0.90, a 95% Hausdorff Distance (HD95) of 1.35 mm, and an Average Symmetric Surface Distance (ASSD) of 0.45 mm, showcasing its segmentation accuracy and robustness. Furthermore, our method outperforms these methods by reducing training time from several days to a few hours while providing a processing time of less than a second per subject. The source code and trained model will be made publicly available on GitHub.

Details DOI

IJCAI Conference 2024 Conference Paper

Resolving Word Vagueness with Scenario-guided Adapter for Natural Language Inference

Yonghao Liu
Mengyu Li
Di Liang
Ximing Li
Fausto Giunchiglia
Lan Huang
Xiaoyue Feng
Renchu Guan

Natural Language Inference (NLI) is a crucial task in natural language processing that involves determining the relationship between two sentences, typically referred to as the premise and the hypothesis. However, traditional NLI models solely rely on the semantic information inherent in independent sentences and lack relevant situational visual information, which can hinder a complete understanding of the intended meaning of the sentences due to the ambiguity and vagueness of language. To address this challenge, we propose an innovative ScenaFuse adapter that simultaneously integrates large-scale pre-trained linguistic knowledge and relevant visual information for NLI tasks. Specifically, we first design an image-sentence interaction module to incorporate visuals into the attention mechanism of the pre-trained model, allowing the two modalities to interact comprehensively. Furthermore, we introduce an image-sentence fusion module that can adaptively integrate visual information from images and semantic information from sentences. By incorporating relevant visual information and leveraging linguistic knowledge, our approach bridges the gap between language and vision, leading to improved understanding and inference capabilities in NLI tasks. Extensive benchmark experiments demonstrate that our proposed ScenaFuse, a scenario-guided approach, consistently boosts NLI performance.

PDF Details DOI

JMLR Journal 2023 Journal Article

Importance Sparsification for Sinkhorn Algorithm

Mengyu Li
Jun Yu
Tao Li
Cheng Meng

Sinkhorn algorithm has been used pervasively to approximate the solution to optimal transport (OT) and unbalanced optimal transport (UOT) problems. However, its practical application is limited due to the high computational complexity. To alleviate the computational burden, we propose a novel importance sparsification method, called Spar-Sink, to efficiently approximate entropy-regularized OT and UOT solutions. Specifically, our method employs natural upper bounds for unknown optimal transport plans to establish effective sampling probabilities, and constructs a sparse kernel matrix to accelerate Sinkhorn iterations, reducing the computational cost of each iteration from $O(n^2)$ to $\widetilde{O}(n)$ for a sample of size $n$. Theoretically, we show the proposed estimators for the regularized OT and UOT problems are consistent under mild regularity conditions. Experiments on various synthetic data demonstrate Spar-Sink outperforms mainstream competitors in terms of both estimation error and speed. A real-world echocardiogram data analysis shows Spar-Sink can effectively estimate and visualize cardiac cycles, from which one can identify heart failure and arrhythmia. To evaluate the numerical accuracy of cardiac cycle prediction, we consider the task of predicting the end-systole time point using the end-diastole one. Results show Spar-Sink performs as well as the classical Sinkhorn algorithm, requiring significantly less computational time. [abs] [ pdf ][ bib ] [ code ] &copy JMLR 2023. ( edit, beta )

PDF Details

IJCAI Conference 2023 Conference Paper

Local and Global: Temporal Question Answering via Information Fusion

Yonghao Liu
Di Liang
Mengyu Li
Fausto Giunchiglia
Ximing Li
Sirui Wang
Wei Wu
Lan Huang

Many models that leverage knowledge graphs (KGs) have recently demonstrated remarkable success in question answering (QA) tasks. In the real world, many facts contained in KGs are time-constrained thus temporal KGQA has received increasing attention. Despite the fruitful efforts of previous models in temporal KGQA, they still have several limitations. (I) They neither emphasize the graph structural information between entities in KGs nor explicitly utilize a multi-hop relation path through graph neural networks to enhance answer prediction. (II) They adopt pre-trained language models (LMs) to obtain question representations, focusing merely on the global information related to the question while not highlighting the local information of the entities in KGs. To address these limitations, we introduce a novel model that simultaneously explores both Local information and Global information for the task of temporal KGQA (LGQA). Specifically, we first introduce an auxiliary task in the temporal KG embedding procedure to make timestamp embeddings time-order aware. Then, we design information fusion layers that effectively incorporate local and global information to deepen question understanding. We conduct extensive experiments on two benchmarks, and LGQA significantly outperforms previous state-of-the-art models, especially in difficult questions. Moreover, LGQA can generate interpretable and trustworthy predictions.

PDF Details DOI