// 中文简历
卢望龙
加拿大纳斯达克 AI/Analytics 高级数据科学家，研究方向包括生成式视觉、图像修复、图像编辑、模式识别、参数高效微调和多模态生成式 AI 系统。
卢望龙现担任加拿大纳斯达克人工智能/分析领域高级数据科学家。2021年获温州大学计算机工学硕士学位，2025年获纽芬兰纪念大学计算机博士学位，研究方向为模式识别、图像编辑与重建、参数高效微调以及可扩展多模态/生成式 AI 系统。已联合发表20余篇高水平论文，涵盖TVCG、ECCV、Pattern Recognition、CVMJ、TNNLS、TCSVT、Information Fusion 等期刊和会议，并获得4项国家发明专利授权。同时担任TIP、TMM、TCSVT、Pattern Recognition、Neurocomputing、KBS、JVCI、Displays等国际期刊和会议的审稿人。
教育背景
- 2021-2025 加拿大纽芬兰纪念大学-计算机科学博士
- 2018-2021 温州大学计算机科学与人工智能学院-计算机软件与理论-工学硕士
- 2014-2018 浙江传媒学院-数字媒体技术-工学学士
研究兴趣
- 计算机视觉, 模式识别, 生成式模型, 图像编辑与修复, 参数高效微调, 多模态 AI, 金融 AI
发表
- Tuning-Free Latent Diffusion Models for Ultrahigh-Resolution Image Editing
Wanglong Lu, Lingming Su, Kaijie Shi, Minglun Gong, Xiaogang Jin, Hanli Zhao, Xianta Jiang
IEEE Transactions on Neural Networks and Learning Systems, 1-15, 2026
[paper] [pdf] [html] [code] - UHDRes: Ultra-High-Definition Image Restoration via Dual-Domain Decoupled Spectral Modulation
Shihao Zhao, Wanglong Lu, Binhao Wang, Tao Wang, Kaihao Zhang, Hanli Zhao
IEEE Transactions on Circuits and Systems for Video Technology, 2026
[paper] [pdf] [html] [code] - Simulation-Driven Imitation Learning for Biosignals-Free Shared-Autonomy Prosthetic Grasping
Kaijie Shi, Wanglong Lu, Han Chen, Vinicius Prado da Fonseca, Ting Zou, Hanli Zhao, Xianta Jiang
arXiv preprint arXiv:2606.07389, 2026
[paper] - EchoSR: Efficient Context Harnessing for Lightweight Image Super-Resolution
Hanli Zhao, Binhao Wang, Shihao Zhao, Tao Wang, Kaihao Zhang, Wanglong Lu
Information Fusion, 104471, 2026
[paper] [pdf] [arXiv] [html] [doi] [code] - AdaMSS: Adaptive Multi-Subspace Approach for Parameter-Efficient Fine-Tuning
Jingjing Zheng, Wanglong Lu, Yiming Dong, Chaojie Ji, Yankai Cao, Zhouchen Lin
NeurIPS 2025, 2025
[paper] [code] [project] - GRIG: Data-Efficient Generative Residual Image Inpainting
Wanglong Lu, Xianta Jiang, Xiaogang Jin, Yong-Liang Yang, Minglun Gong, Kaijie Shi, Tao Wang, Hanli Zhao
Computational Visual Media 11(6), 1329-1361, 2025
[paper] [pdf] [arXiv] [doi] [project] - StDDPM: Sequential Financial Synthetic Data Generation using T-distribution based Diffusion Model
Omid Tarkhaneh, Hamideh Mehri, Wanglong Lu, Farzaneh Shoeleh, Vinicius Veloso de Melo
Research Square preprint, 2025
[paper] [pdf] - Toward Biosignals-Free Autonomous Prosthetic Hand Control via Imitation Learning
Kaijie Shi, Wanglong Lu, Hanli Zhao, Vinicius Prado da Fonseca, Ting Zou, Xianta Jiang
IEEE Transactions on Neural Systems and Rehabilitation Engineering 33, 3544-3554, 2025
[paper] [pdf] [arXiv] [doi] [project] - Real-time dual-eye collaborative eyeblink detection with contrastive learning
Hanli Zhao, Yu Wang , Wanglong Lu, Zili Yi, Jun Liu∗, Minglun Gong
Pattern Recognition, 2025
[paper] - Visual style prompt learning using diffusion models for blind face restoration
Wanglong Lu, Jikai Wang, Tao Wang, Kaihao Zhang, Xianta Jiang, Hanli Zhao*
Pattern Recognition, 2025
[paper] [code] - Degradation-Aware Frequency-Separated Transformer for Blind Super-Resolution
Hanli Zhao, Binhao Wang, Wanglong Lu*, Juncong Lin
International Conference on Computational Visual Media, 2025
[paper] - TextDoctor: Unified Document Image Inpainting via Patch Pyramid Diffusion Models
Wanglong Lu, Lingming Su, Jingjing Zheng, Vinícius Veloso de Melo, Farzaneh Shoeleh, John Hawkin, Terrence Tricco, Hanli Zhao, Xianta Jiang
ArXiv, 2025
[paper] - Do Inpainting Yourself: Generative Facial Inpainting Guided by Exemplars
Wanglong Lu, Hanli Zhao, Xianta Jiang, Xiaogang Jin, Yongliang Yang, Min Wang, Jiankai Lyu, and Kaijie Shi
Neurocomputing 617, 128996, 2025
[paper] [code] - Generative Models for Semantic Facial Image Editing: Multimodal Approaches
Wanglong Lu
PhD thesis, Memorial University of Newfoundland, 2025
[paper] - FACEMUG: A Multimodal Generative and Fusion Framework for Local Facial Editing
Wanglong Lu, Jikai Wang, Xiaogang Jin, Xianta Jiang, and Hanli Zhao∗
IEEE Transactions on Visualization and Computer Graphics, 2024
[paper] - Handling the Non-smooth Challenge in Tensor SVD: A Multi-objective Tensor Recovery Framework
Jingjing Zheng, Wanglong Lu, Wenzhe Wang, Yankai Cao*, Xiaoqin Zhang, and Xianta Jiang
ECCV, 2024
[paper] - Promptrr: Diffusion models as prompt generators for single image reflection removal
Tao Wang, Wanglong Lu, Kaihao Zhang, Wenhan Luo, Tae-Kyun Kim, Tong Lu, Hongdong Li, Ming-Hsuan Yang
ArXiv, 2024
[paper] - TEG: image theme recognition using text-embedding-guided few-shot adaptation
Jikai Wang, Wanglong Lu, Yu Wang, Kaijie Shi, Xianta Jiang, Hanli Zhao
Journal of Electronic Imaging 33(1), 013028, 2024
[paper] [doi] - Restoring Vision in Hazy Weather with Hierarchical Contrastive Learning
Tao Wang, Guangpin Tao, Wanglong Lu, Kaihao Zhang, Wenhan Luo, Xiaoqin Zhang, Tong Lu.
Pattern Recognition Volume 145, January 2024, 109956, 2024
[paper] [doi] [cite] - Detecting Blinks from Wearable Cameras using Spatial-Temporal-Aware Deep Network Learning
Yu Wang, Wanglong Lu, Hanli Zhao, Xianta Jiang∗, Bin Zheng, M. Stella Atkins.
ETRA 23, 2023
[paper] [doi] [cite] - 基于多尺度特征先验的图像拼接篡改检测
吕建凯, 卢望龙, 王敏, 刘影, 史开杭, 黄辉, 赵汉理
China Sciencepaper 17(11), 2022 - Generative image inpainting with enhanced gated convolution and Transformers
Min Wang, Wanglong Lu, Jiankai Lyu, Kaijie Shi, Hanli Zhao.
Displays 76, 102321, 2022
[paper] [doi] [cite] - Efficient Generative Face Completion with Perceptual Deblurring
Hanli Zhao, Ying Liu, Wanglong Lu, Xiaogang Jin, Hui Huang, Kaijie Shi
Journal of Computer-Aided Design & Computer Graphics 34(9), 1420-1431, 2022 - 基于感知去模糊的高效人脸图像修复算法
赵汉理, 刘影, 卢望龙, 金小刚, 黄辉, 史开杭
计算机辅助设计与图形学学报 34(9), 1420-1431, 2022 - 基于概率的深度可分离卷积网络通道剪枝
赵汉理, 史开杭, 金小刚, 徐明亮, 黄辉, 卢望龙, 刘影
计算机科学技术学报 37(3), 584-600, 2022 - Probability-Based Channel Pruning for Depthwise Separable Convolutional Networks
Han-Li Zhao, Kai-Jie Shi, Xiaogang Jin, Ming-Liang Xu, Hui Huang, Wang-Long Lu, Ying Liu.
Journal of Computer Science and Technology 37, 584-600, 2022
[paper] [doi] - Category-consistent deep network learning for accurate vehicle logo recognition
Wanglong Lu, Hanli Zhao, Qi He, Hui Huang, Xiaogang Jin.
Neurocomputing 463, 623-636, 2021
[paper] [doi] [cite] [code] - High‐quality retinal vessel segmentation using generative adversarial network with a large receptive field
Hanli Zhao, Xiaqing Qiu, Wanglong Lu, Hui Huang, Xiaogang Jin.
International Journal of Imaging Systems and Technology 30(3), 828-842, 2020
[paper] [doi]
专利
- 2023-06 一种基于类别一致性深度学习的图像识别方法. 国家发明专利, 赵汉理, 卢望龙, 何奇, 黄辉. 专利号：ZL 2021 1 0408724.X
- 2021-05 一种基于卷积神经网络深度特征的车标识别方法. 国家发明专利, 赵汉理, 卢望龙, 陈强. 专利号：ZL 2020 1 0139043.3
- 2021-07 一种基于GAN的视网膜血管图像智能分割方法. 国家发明专利, 赵汉理, 卢望龙, 邱夏青, 黄辉. 专利号：ZL 2019 1 0884346.5
- 2021-09 一种基于卷积神经网络的车标智能检测方法. 国家发明专利, 赵汉理, 卢望龙. 专利号：ZL 2020 1 0139068.3
部分荣誉
- 2024-04 温州市计算机学会学生会员计算机创新创业奖 (一等奖，队长)
- 2023-04 纪念大学计算机科学系杰出研究奖 (博士)
- 2022-05 Mitacs Accelerate Award
- 2020-12 温州大学优秀毕业生 (研究生)
- 2019-12 全国研究生数学建模大赛(三等奖)
- 2019-07 大学生程序设计大赛(CCPC)-江西省大学生程序设计大赛中国江西省(三等奖，队长)
- 2018-06 浙江省优秀毕业生
- 2017-12 浙江省政府奖学金，浙江省
- 2017-07 第十届中国大学生计算机设计大赛服务外包 “泊乐-智能路侧泊车系统” (二等奖)
- 2016-12 浙江省政府奖学金，浙江省
- 2015-12 中国浙江传媒学院优秀学生干部
工作经历
2025.03-至今 高级数据科学家，AI/Analytics，Nasdaq，St. John’s，NL，加拿大
- 2024.05-2025.01 AI 算法实习生，Nasdaq Verafin，St. John’s，NL，加拿大
- 设计基于扩散模型的文本档案图像修复算法 [TextDoctor]
- 设计基于 Patch Gaussian Latent Discriminant Modeling 的图像验证算法
- 2017.12-2018.08 人工智能算法实习生，杭州中控瀚联电子商务有限公司，杭州，中国
- 汽车标志图像分析与处理
- 协助开发图像标注工具
- 参与车标识别算法设计
- 2022.07-2022.11 AI 实习生, Beaufort Solutions Inc. , 1 Church Hill, St. John’s, NL A1C 3Z7, Canada
- 图像主题分类算法的设计与构建
教学经历
2021.09-2021.12 数据结构与算法课程助教, Data Structures and Algorithms, 纽芬兰纪念大学, 加拿大
2024.01-2024.04 初阶机器学习课程助教, Introduction to Machine Learning, 纽芬兰纪念大学, 加拿大