Author name cluster

Yuping Wang

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.

5 papers

1 author row

EAAI Journal 2026 Journal Article

Investigation on intelligent surface roughness prediction considering chatter effects based on fine-grained feature extraction and fusion

Liangshi Sun
Xianzhen Huang
Zhiyuan Jiang
Yongchao Zhang
Chengying Zhao
Yuping Wang

In the field of smart manufacturing, the accurate prediction of surface roughness is considered one of the key challenges in improving machining quality. Chatter is a common occurrence in the machining process and has a significant impact on machining quality, especially during high-speed milling. However, many existing methods often overlook the effect of chatter, which severely limits their application in engineering practice. To address this issue, the study developed an intelligent surface roughness prediction method that takes into account the chatter effects. First, the sensor signals from online monitoring are denoised and decomposed using wavelet packet decomposition and successive variational mode decomposition, and then multi-dimensional fine-grained features are extracted from multiple domains. Next, a fine-grained feature fusion network is proposed to learn the complex coupled effects of inherent processes and milling chatter on surface roughness and achieve surface roughness prediction with uncertainty quantification. Finally, the effectiveness and accuracy of the proposed method are demonstrated through real-world high-speed milling experiments. Compared to conventional deep learning methods, the proposed method yields superior predictive performance. Furthermore, ablation experiments further validate the effectiveness of each contributing factor. Therefore, this study can provide theoretical guidance for surface roughness prediction considering chatter effects in complex machining environments.

Details DOI

YNICL Journal 2025 Journal Article

CTV-MIND: A cortical thickness-volume integrated individualized morphological network model to explore disease progression in temporal lobe epilepsy

Xinyan Liu
Jiaqi Han
Xiating Zhang
Boxuan Wei
Lu Xu
Qilin Zhou
Yuping Wang
Yicong Lin

Temporal lobe epilepsy (TLE) is a progressive brain network disorder. Elucidating network reorganization and identifying disease progression-associated biomarkers are crucial for understanding pathological mechanisms, quantifying disease burden, and optimizing clinical strategies. This study aimed to investigate progressive changes in TLE by constructing a novel individualized morphological brain network based on T1-weighted structural magnetic resonance imaging (MRI). MRI data were collected from 34 postoperative seizure-free TLE patients and 28 age- and sex-matched healthy controls (HC), with patients divided into LONG-TERM and SHORT-TERM groups. Individualized morphological networks were constructed using the Morphometric INverse Divergence (MIND) framework by integrating cortical thickness and volume features (CTV-MIND). Network properties were then calculated and compared across groups to identify features potentially associated with disease progression. Results revealed progressive hub-node reorganization in CTV-MIND networks, with the LONG-TERM group showing increased connectivity in the lesion-side temporal lobe compared to SHORT-TERM and HC groups. The altered network node properties showed a significant correlation with local cortical atrophy. Incorporating identified network features into a machine learning-based brain age prediction model further revealed significantly elevated brain age in TLE. Notably, duration-related brain regions exerted a more significant and specific impact on premature brain aging in TLE than other regional combinations. Thus, prolonged duration may serve as an important contributor to the pathological aging observed in TLE. Our findings could help clinicians better identify abnormal brain trajectories in TLE and have the potential to facilitate the optimization of personalized treatment strategies.

Details DOI

AAAI Conference 2025 Conference Paper

Language Model Can Listen While Speaking

Ziyang Ma
Yakun Song
Chenpeng Du
Jian Cong
Zhuo Chen
Yuping Wang
Yuxuan Wang
Xie Chen

Dialogue serves as the most natural manner of human-computer interaction (HCI). Recent advancements in speech language models (SLM), have significantly enhanced speech-based conversational AI. However, these models are limited to turn-based conversation, lacking the ability to interact with humans in real-time spoken scenarios, for example, being interrupted when the generated content is not satisfactory. To address these limitations, we explore full duplex modeling (FDM) in interactive speech language models (iSLM), focusing on enhancing real-time interaction and, more explicitly, exploring the quintessential ability of interruption. We introduce a novel model design, namely listening-while-speaking language model (LSLM), an end-to-end system equipped with both listening and speaking channels. Our LSLM employs a token-based decoder-only TTS for speech generation and a streaming self-supervised learning (SSL) encoder for real-time audio input. LSLM fuses both channels for autoregressive generation and detects turn-taking in real time. Three fusion strategies—early fusion, middle fusion, and late fusion—are explored, with middle fusion achieving an optimal balance between speech generation and real-time interaction. Two experimental settings, command-based FDM and voice-based FDM, demonstrate LSLM’s robustness to noise and sensitivity to diverse instructions. Our results highlight LSLM’s capability to achieve duplex communication with minimal impact on existing systems. This study aims to advance the development of interactive speech dialogue systems, enhancing their applicability in real-world contexts.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

RDD: Retrieval-Based Demonstration Decomposer for Planner Alignment in Long-Horizon Tasks

Mingxuan Yan
Yuping Wang
Zechun Liu
Jiachen Li

To tackle long-horizon tasks, recent hierarchical vision-language-action (VLAs) frameworks employ vision-language model (VLM)-based planners to decompose complex manipulation tasks into simpler sub-tasks that low-level visuomotor policies can handle. Typically, the VLM planner needs finetuning to learn to decompose a new task, which requires target task demonstrations segmented into sub-tasks by either human annotation or heuristic rules. However, without prior knowledge, the heuristic sub-tasks can deviate significantly from the visuomotor policy's training data, thereby degrading task performance. To address these issues, we propose a Retrieval-based Demonstration Decomposer (RDD) that automatically decomposes video demonstrations into sub-tasks with prior by aligning the visual features of the decomposed sub-task intervals with those from the training data of the low-level visuomotor policies. RDD outperforms the state-of-the-art sub-task decomposer on both simulation and real-world tasks, demonstrating robustness across diverse settings. Code and more results are available at https: //rdd-neurips. github. io

PDF Details

AIJ Journal 2015 Journal Article

Optimizing ontology alignments through a Memetic Algorithm using both MatchFmeasure and Unanimous Improvement Ratio

Xingsi Xue
Yuping Wang

There are three main drawbacks of current evolutionary approaches for determining the weights of ontology matching system. The first drawback is that it is difficult to simultaneously deal with several pairs of ontologies, i. e. finding a universal weight configuration that can be used for different ontology pairs without adjustment. The second one is that a reference alignment between two ontologies to be aligned should be given in advance which could be very expensive to obtain especially when the scale of ontologies is considerably large. The last one arises from f-measure, a generally used evaluation metric of the alignment's quality, which may cause the bias improvement of the solution. To overcome these three defects, in this paper, we propose to use both MatchFmeasure, a rough evaluation metric on no reference alignment to approximate f-measure, and Unanimous Improvement Ratio (UIR), a measure that complements MatchFmeasure, in the process of optimizing the ontology alignments by Memetic Algorithm (MA). The experimental results have shown that the MA using both MatchFmeasure and UIR is effective to simultaneously align multiple pairs of ontologies and avoid the bias improvement caused by MatchFeasure. Moreover, the comparison with state-of-the-art ontology matching systems further indicates the effectiveness of the proposed method.

Details DOI