郑旭｜长沙理工大学｜学者主页

2026

基于卷积神经网络的汽车车身声传函预测模型研究

唐冬林，刘迟，郑旭，邱毅

《现代机械》

DOI

2026

基于流固耦合与深度学习算法的非工况双平臂塔机风致响应研究

吴彦伟，郑旭，邱海江，吕念

《自动化与仪器仪表》

2026

三轴振动激励下的坐姿人体身体振动传递特性预测研究

孙超，刘迟，郑旭，邱毅，项磊

《振动工程学报》

DOI

2026

热-振双物理场环境对人体舒适性的耦合作用研究

王歆宇，刘迟，邱毅，郑旭，林泽峰，尹玮倓

《振动工程学报》

DOI

2026

宽窄带混合噪声的多目标优化控制方法研究

刘学贤，郑旭，贾梓镔，励汝彬

《振动工程学报》

2026

基于时空数据的大跨度高速铁路桥梁影响系数动态反演方法研究

郑涵文，伊廷华，郑旭，杨东辉，刘华，赵欣欣

《建筑结构学报》

DOI

2026

车内乘员耳区声场复现与客观评价研究

卢璐，郑旭，刘迟，于泳

《振动与冲击》

2026

电梯曳引机电磁噪声的修正半解析模型研究

孙艳红，郑旭

《中国机械工程》

2026

DVD: Deterministic Video Depth Estimation with Generative Priors

Hong-Fei Zhang, Harold Haodong Chen, Chenfei Liao, Jing He, Zi-Xin Zhang, Haodong Li, Yihao Liang, Kanghao Chen, B. Ren, Xu Zheng, Shuai Yang, Kun Zhou, Yin-Chuan Li, Nicu Sebe, Yingke Chen

arXiv.org

DOI

2026

StruVis: Enhancing Reasoning-based Text-to-Image Generation via Thinking with Structured Vision

Yuanhuiyi Lyu, Kaiyu Lei, Ziqiao Weng, Xu Zheng, Lutao Jiang, Tengjie Li, Yangfu Li, Ziyuan Huang, Lin-Feng Zhang, Xuming Hu

arXiv.org

DOI

2026

Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrieval

Yibo Yan, Jiahao Huo, Guanbo Feng, Mingdong Ou, Yiqun Cao, Xin Zou, Shuliang Liu, Yuanhuiyi Lyu, Yue Huang, Jun-Gang Li, Ke-Ning Zheng, Xu Zheng, Philip S. Yu, James T. Kwok, Xu-Ming Hu

arXiv.org

DOI

2026

Seg-Agent: Test-Time Multimodal Reasoning for Training-Free Language-Guided Segmentation

Chao Hao, Ju Xu, Ji Du, Shuo Ye, Ziyue Qiao, Xiaodong Cun, Guangcong Wang, Xu Zheng, Zitong Yu

arXiv.org

DOI

2026

OmniCoT: A Benchmark for Global and Multi-Step Panoramic Reasoning

Haocong He, Chenfei Liao, Zichen Wen, Zihao Dongfang, Xu Zheng, Bin Ren, Chang Su, Zi-Xin Zhang, Harold Haodong Chen, Hong-Fei Zhang, Wei-Jia Li, Kailun Yang, Conghui He, Xuming Hu, Nicu Sebe, Lin-Feng Zhang

arXiv.org

DOI

2026

EgoIntent: An Egocentric Step-level Benchmark for Understanding What, Why, and Next

Ye Pan, Chifai Wong, Yuanhuiyi Lyu, Hanqian Li, Jiahao Huo, Jiacheng Chen, Lutao Jiang, Xu Zheng, Xu-Ming Hu

arXiv.org

DOI

2026

Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation

Chifai Wong, Ye Pan, Yuanhuiyi Lyu, Xu Zheng, Zi-Dong Cao, Lutao Jiang, Zi-Xin Zhang, Hui-Yu Zhou, Xuming Hu

arXiv.org

DOI

2026

OnceSelect: Reusable Data Selection for Efficient Multimodal Instruction Tuning

Ming-Kang Dong, Mu-Xin Pu, Hong-Yi Cai, Jie Li, Jiancheng Pan, Xu Zheng, Ya-Dan Luo, Yu-Qian Fu

2026

EgoOmniWorld: Unifying Egocentric Understanding via Ego-Action-World Interactions

Song-Ruo Chen, Yu-Qian Fu, Yu Li, Ming-Kang Dong, Si-Fan Zhou, Bin Ren, Xu Zheng, Tianwen Qian, Mohamed Elhoseiny, Yan-Wei Fu

2026

ObjectStream: Latent Objects as Memory Anchors for Streaming Video Understanding

Ming-Kang Dong, Mu-Xin Pu, Jie Li, Bohan Guo, Song-Ruo Chen, Bin Ren, Xu Zheng, Chenlan Zhao, Tianwen Qian, Mohamed Elhoseiny, Yu-Qian Fu

arXiv.org

DOI

2026

SoulX-LiveAct: Towards Hour-Scale Real-Time Human Animation with Neighbor Forcing and ConvKV Memory

Dingcheng Zhen, Xu Zheng, Ruixin Zhang, Zhiqi Jiang, Yichao Yan, Ming Tao, Shunshun Yin

arXiv.org

DOI

2025

基于振动测试和机器学习的发动机噪声预测

王钰涵，郑旭，周南，李威霖，陈锋

《振动、测试与诊断》

DOI

2025

DiMeR: Disentangled Mesh Reconstruction Model

Lutao Jiang, Jian-Tao Lin, Kanghao Chen, Wen-Hang Ge, Xin Yang, Yi-Fan Jiang, Yuanhuiyi Lyu, Xu Zheng, Ying-Cong Chen

arXiv.org

DOI

2025

PANORAMA: The Rise of Omnidirectional Vision in the Embodied AI Era

Xu Zheng, Chenfei Liao, Ziqiao Weng, Kaiyu Lei, Zihao Dongfang, Haocong He, Yuanhuiyi Lyu, Lutao Jiang, Lu Qi, Li Chen, D. Paudel, Kailun Yang, Lin-Feng Zhang, Luc Van Gool, Xuming Hu

arXiv.org

DOI

2025

Are We Using the Right Benchmark: An Evaluation Framework for Visual Token Compression Methods

Chenfei Liao, Wensong Wang, Zichen Wen, Xu Zheng, Yi-Yu Wang, Haocong He, Yuanhuiyi Lyu, Lutao Jiang, Xin Zou, Yu-Qian Fu, Bin Ren, Lin-Feng Zhang, Xuming Hu

Annual Meeting of the Association for Computational Linguistics

DOI

2025

OmniSAM: Omnidirectional Segment Anything Model for UDA in Panoramic Semantic Segmentation

Ding Zhong, Xu Zheng, Chenfei Liao, Yuanhuiyi Lyu, Jia-Lei Chen, Sheng Wu, Lin-Feng Zhang, Xuming Hu

IEEE International Conference on Computer Vision

DOI

2025

Are Multimodal Large Language Models Ready for Omnidirectional Spatial Reasoning?

Zihao Dongfang, Xu Zheng, Ziqiao Weng, Yuanhuiyi Lyu, D. Paudel, Luc Van Gool, Kailun Yang, Xuming Hu

2026 IEEE/CVF Conference on Computer Vision and Pattern Recognition- FINDINGS Track (CVPRF)

DOI

2025

MLLMs are Deeply Affected by Modality Bias

Xu Zheng, Chenfei Liao, Yu-Qian Fu, Kaiyu Lei, Yuanhuiyi Lyu, Lutao Jiang, Bin Ren, Jia-Lei Chen, Jia-Wen Wang, Cheng-Xi Li, Lin-Feng Zhang, D. Paudel, Xuanjing Huang, Yu-Gang Jiang, N. Sebe, Dacheng Tao, Luc Van Gool, Xuming Hu

arXiv.org

DOI

2025

Reducing Unimodal Bias in Multi-Modal Semantic Segmentation With Multi-Scale Functional Entropy Regularization

Xu Zheng, Yuanhuiyi Lyu, Lutao Jiang, D. Paudel, Luc Van Gool, Xuming Hu

IEEE International Conference on Computer Vision

DOI

2025

Retrieval Augmented Generation and Understanding in Vision: A Survey and New Outlook

Xu Zheng, Ziqiao Weng, Yuanhuiyi Lyu, Lutao Jiang, Haiwei Xue, B. Ren, D. Paudel, N. Sebe, Luc Van Gool, Xuming Hu

arXiv.org

DOI

2025

Understanding-in-Generation: Reinforcing Generative Capability of Unified Model via Infusing Understanding into Generation

Yuanhuiyi Lyu, Chifai Wong, Chenfei Liao, Lutao Jiang, Xu Zheng, Ze-Xin Lu, Lin-Feng Zhang, Xuming Hu

arXiv.org

DOI

2025

RealRAG: Retrieval-augmented Realistic Image Generation via Self-reflective Contrastive Learning

Yuanhuiyi Lyu, Xu Zheng, Lutao Jiang, Yibo Yan, Xin Zou, Hui-Yu Zhou, Lin-Feng Zhang, Xu-Ming Hu

International Conference on Machine Learning

DOI

2025

Benchmarking Multi-Modal Semantic Segmentation Under Sensor Failures: Missing and Noisy Modality Robustness

Chenfei Liao, Kaiyu Lei, Xu Zheng, J. Moon, Zhi-Xiong Wang, Yixuan Wang, D. Paudel, L. van Gool, Xuming Hu

2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

DOI

2025

MMUnlearner: Reformulating Multimodal Machine Unlearning in the Era of Multimodal Large Language Models

Jiahao Huo, Yibo Yan, Xu Zheng, Yuanhuiyi Lyu, Xin Zou, Zhihua Wei, Xu-Ming Hu

Annual Meeting of the Association for Computational Linguistics

DOI

2025

Marrying Autoregressive Transformer and Diffusion with Multi-Reference Autoregression

Dingcheng Zhen, Qian Qiao, Xu Zheng, Tan Yu, Kan Wu, Zi-Wei Zhang, Siyuan Liu, Shunshun Yin, Ming Tao

arXiv.org

DOI

2025

Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarks

Xu Zheng, Zihao Dongfang, Lutao Jiang, Bo-Yuan Zheng, Yulong Guo, Zhenquan Zhang, Giuliano Albanese, Run-Yi Yang, Meng-Jiao Ma, Zi-Xin Zhang, Chenfei Liao, Dingcheng Zhen, Yuanhuiyi Lyu, Yu-Qian Fu, Bin Ren, Lin-Feng Zhang, D. Paudel, N. Sebe, Luc Van Gool, Xuming Hu

arXiv.org

DOI

2025

MemorySAM: Memorize Modalities and Semantics with Segment Anything Model 2 for Multi-modal Semantic Segmentation

Chenfei Liao, Xu Zheng, Yuanhuiyi Lyu, Haiwei Xue, Yihong Cao, Jia-Wen Wang, Kailun Yang, Xuming Hu

arXiv.org

DOI

2025

AI for Service: Proactive Assistance with AI Glasses

Zichen Wen, Yi-Yu Wang, Chenfei Liao, Bo-Xue Yang, Junxian Li, Wei-Feng Liu, Haocong He, Bo-Han Feng, Xu-Yang Liu, Yuanhuiyi Lyu, Xu Zheng, Xuming Hu, Lin-Feng Zhang

arXiv.org

DOI

2025

Shifting AI Efficiency From Model-Centric to Data-Centric Compression

Xu-Yang Liu, Zichen Wen, Shao-Bo Wang, Junjie Chen, Zhishan Tao, Yubo Wang, Xiangqi Jin, Chang Zou, Yi-Yu Wang, Chenfei Liao, Xu Zheng, Hong-Gang Chen, Wei-Jia Li, Xuming Hu, Conghui He, Lin-Feng Zhang

arXiv.org

DOI

2025

PhysToolBench: Benchmarking Physical Tool Understanding for MLLMs

Zi-Xin Zhang, Kanghao Chen, Xin Lin, Lu-Tao Jiang, Xu Zheng, Yuanhuiyi Lyu, Li-Tao Guo, Yin-Chuan Li, Ying-cong Chen

arXiv.org

DOI

2025

Don't Just Chase "Highlighted Tokens" in MLLMs: Revisiting Visual Holistic Context Retention

Xin Zou, Di Lu, Yizhou Wang, Yibo Yan, Yuanhuiyi Lyu, Xu Zheng, Lin-Feng Zhang, Xuming Hu

Neural Information Processing Systems

DOI

2024

基于时序图推理的设备剩余使用寿命预测

刘雨蒙，郑旭，田玲，王宏安

《自动化学报》

DOI

2024

牵引电机空载声品质预测模型研究

张伟，庞聪，于泳，朱一乔，邱毅，郑旭

《微电机》

2024

An improved deep Q-learning algorithm for a trade-off between energy consumption and productivity in batch scheduling

Xu Zheng, Zhen Chen

Computers & Industrial Engineering

DOI

2024

BrightDreamer: Generic 3D Gaussian Generative Framework for Fast Text-to-3D Synthesis

Lutao Jiang, Xu Zheng, Yuanhuiyi Lyu, Jia-Zhou Zhou, Lin Wang

Trans. Mach. Learn. Res.

DOI

2024

SAVEn-Vid: Synergistic Audio-Visual Integration for Enhanced Understanding in Long Video Context

Jun-Gang Li, Sicheng Tao, Yibo Yan, Xiaojie Gu, Hao-Dong Xu, Xu Zheng, Yuanhuiyi Lyu, Lin-Feng Zhang, Xuming Hu

arXiv.org

DOI

2024

A Survey of Mathematical Reasoning in the Era of Multimodal Large Language Model: Benchmark, Method & Challenges

Yibo Yan, Jiamin Su, Jianxiang He, Fangteng Fu, Xu Zheng, Yuanhuiyi Lyu, Kun Wang, Shen Wang, Qing-Song Wen, Xu-Ming Hu

Annual Meeting of the Association for Computational Linguistics

DOI

2024

Learning Robust Anymodal Segmentor with Unimodal and Cross-modal Distillation

Xu Zheng, Haiwei Xue, Jia-Lei Chen, Yibo Yan, Lutao Jiang, Yuanhuiyi Lyu, Kailun Yang, Lin-Feng Zhang, Xuming Hu

arXiv.org

DOI

2014

产学协同——行业大学立德树人人才培养体系构建

郑旭，王颍颍，吴爱萍

《现代教育管理》，No. 9

下载原文

2010

基于BP神经网络的电解加工工艺参数优选研究

郑旭，康敏，傅秀清

《电加工与模具》

2007

产学研合作教育的理念与制度探析

郑旭

《大连理工大学学报(社会科学版)》，No. 4

下载原文

精选作品

期刊论文

基于卷积神经网络的汽车车身声传函预测模型研究

基于流固耦合与深度学习算法的非工况双平臂塔机风致响应研究

三轴振动激励下的坐姿人体身体振动传递特性预测研究

热-振双物理场环境对人体舒适性的耦合作用研究

宽窄带混合噪声的多目标优化控制方法研究

基于时空数据的大跨度高速铁路桥梁影响系数动态反演方法研究

车内乘员耳区声场复现与客观评价研究

电梯曳引机电磁噪声的修正半解析模型研究

DVD: Deterministic Video Depth Estimation with Generative Priors

StruVis: Enhancing Reasoning-based Text-to-Image Generation via Thinking with Structured Vision

Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrieval

Seg-Agent: Test-Time Multimodal Reasoning for Training-Free Language-Guided Segmentation

OmniCoT: A Benchmark for Global and Multi-Step Panoramic Reasoning

EgoIntent: An Egocentric Step-level Benchmark for Understanding What, Why, and Next

Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation

OnceSelect: Reusable Data Selection for Efficient Multimodal Instruction Tuning

EgoOmniWorld: Unifying Egocentric Understanding via Ego-Action-World Interactions

ObjectStream: Latent Objects as Memory Anchors for Streaming Video Understanding

SoulX-LiveAct: Towards Hour-Scale Real-Time Human Animation with Neighbor Forcing and ConvKV Memory

基于振动测试和机器学习的发动机噪声预测

DiMeR: Disentangled Mesh Reconstruction Model

PANORAMA: The Rise of Omnidirectional Vision in the Embodied AI Era

Are We Using the Right Benchmark: An Evaluation Framework for Visual Token Compression Methods

OmniSAM: Omnidirectional Segment Anything Model for UDA in Panoramic Semantic Segmentation

Are Multimodal Large Language Models Ready for Omnidirectional Spatial Reasoning?

MLLMs are Deeply Affected by Modality Bias

Reducing Unimodal Bias in Multi-Modal Semantic Segmentation With Multi-Scale Functional Entropy Regularization

Retrieval Augmented Generation and Understanding in Vision: A Survey and New Outlook

Understanding-in-Generation: Reinforcing Generative Capability of Unified Model via Infusing Understanding into Generation

RealRAG: Retrieval-augmented Realistic Image Generation via Self-reflective Contrastive Learning

Benchmarking Multi-Modal Semantic Segmentation Under Sensor Failures: Missing and Noisy Modality Robustness

MMUnlearner: Reformulating Multimodal Machine Unlearning in the Era of Multimodal Large Language Models

Marrying Autoregressive Transformer and Diffusion with Multi-Reference Autoregression

Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarks

MemorySAM: Memorize Modalities and Semantics with Segment Anything Model 2 for Multi-modal Semantic Segmentation

AI for Service: Proactive Assistance with AI Glasses

Shifting AI Efficiency From Model-Centric to Data-Centric Compression

PhysToolBench: Benchmarking Physical Tool Understanding for MLLMs

Don't Just Chase "Highlighted Tokens" in MLLMs: Revisiting Visual Holistic Context Retention

基于时序图推理的设备剩余使用寿命预测

牵引电机空载声品质预测模型研究

An improved deep Q-learning algorithm for a trade-off between energy consumption and productivity in batch scheduling

BrightDreamer: Generic 3D Gaussian Generative Framework for Fast Text-to-3D Synthesis

SAVEn-Vid: Synergistic Audio-Visual Integration for Enhanced Understanding in Long Video Context

A Survey of Mathematical Reasoning in the Era of Multimodal Large Language Model: Benchmark, Method & Challenges

Learning Robust Anymodal Segmentor with Unimodal and Cross-modal Distillation

产学协同——行业大学立德树人人才培养体系构建

基于BP神经网络的电解加工工艺参数优选研究

产学研合作教育的理念与制度探析

研究方向