WL
Wei Liu
cs.CVcs.LGcs.CLcs.AIstat.MLmath.OCeess.IVAlgorithmscs.MMeess.AS
On Valency
published · living versionsW_6um5xyqj·v1 · currentpublished
Going Deeper with Convolutions
with Christian Szegedy, Yangqing Jia, Pierre Sermanet, Scott Reed +4
1 version
Preprints & journals
340 papers in the corpus · 2011–2026LoRA-Composer: Leveraging Low-Rank Adaptation for Multi-Concept Customization in Training-Free Diffusion Models2403.11627v2 · Yang Yang, Wen Wang, Liang Peng et al.2024 · 18 citationsIEEE Transactions on Image Processing, vol. 34, pp. 8145-8158, 2025
A multi-scale dual-stream fusion network for high-accuracy sEMG-based gesture classification.41501380 · He, Dongyi, Liu, Wei, Yan, He et al.2026 · 5 citationsScientific reports. 2026;16(1):4819
Stochastic Gradient Made Stable: A Manifold Propagation Approach for Large-Scale Optimization1506.08350v2 · Yadong Mu, Wei Liu, Wei Fan2015 · 38 citationsarXiv
Stochastic Quasi-Newton Methods for Nonconvex Stochastic Optimization1607.01231v4 · Xiao Wang, Shiqian Ma, Donald Goldfarb et al.2016 · 189 citationsarXiv
A Unified Analysis of AdaGrad with Weighted Aggregation and Momentum Acceleration1808.03408v4 · Li Shen, Congliang Chen, Fangyu Zou et al.2018 · 32 citationsarXiv
A Sufficient Condition for Convergences of Adam and RMSProp1811.09358v3 · Fangyu Zou, Li Shen, Zequn Jie et al.2018 · 435 citationsarXiv
LoDAdaC: a unified local training-based decentralized framework with adaptive gradients and compressed communication2604.09970v1 · Wei Liu, Anweshit Panda, Ujwal Pandey et al.2026 · 0 citationsarXiv
FreqEdit: Preserving High-Frequency Features for Robust Multi-Turn Image Editing2512.01755v2 · Yucheng Liao, Jiajun Liang, Kaiqian Cui et al.2025 · 0 citationsarXiv
Deep Face Restoration: A Survey2211.02831v3 · Tao Wang, Kaihao Zhang, Jiankang Deng et al.2022 · 16 citationsarXiv
Orthogonal Spatial-temporal Distributional Transfer for 4D Generation2603.05081v1 · Wei Liu, Shengqiong Wu, Bobo Li et al.2026 · 0 citationsarXiv
LiePrune: Lie Group and Quantum Geometric Dual Representation for One-Shot Structured Pruning of Quantum Neural Networks2512.09469v1 · Haijian Shao, Bowen Yang, Wei Liu et al.2025 · 0 citationsarXiv
DeID-GPT: Zero-shot Medical Text De-Identification by GPT-42303.11032v3 · Zhengliang Liu, Yue Huang, Xiaowei Yu et al.2023 · 87 citationsarXiv
Evaluating Large Language Models for Radiology Natural Language Processing2307.13693v3 · Zhengliang Liu, Tianyang Zhong, Yiwei Li et al.2023 · 19 citationsarXiv
Global and Local Semantic Completion Learning for Vision-Language Pre-Training.40768455 · Tu, Rong-Cheng, Ji, Yatai, Jiang, Jie et al.2025 · 5 citationsIEEE transactions on pattern analysis and machine intelligence. 2025;47(12):11065-11079
PharmacyGPT: exploration of artificial intelligence for medication management in the intensive care unit.41152866 · Liu, Zhengliang, Xu, Shaochen, Wu, Zihao et al.2025 · 6 citationsBMC medical informatics and decision making. 2025;25(1):398
New Physics Search at the CEPC: a General Perspective2505.24810v2 · Xiaocong Ai, Stefan Antusch, Peter Athron et al.2025 · 13 citationsarXiv
A Benchmark Study of Deep Reinforcement Learning Algorithms for the Container Stowage Planning Problem2510.02589v1 · Yunqi Huang, Nishith Chennakeshava, Alexis Carras et al.2025 · 1 citationarXiv
Boundary Learning by Using Weighted Propagation in Convolution Network1905.09226v3 · Wei Liu, Jiahao Chen, Chuni Liu et al.2019 · 16 citationsJournal of Computational Science, 2022
Cross-period sub-nyquist sampling method for efficient 3D surface profiling in low-coherence scanning interferometry.40515347 · Liu, Wei, Tang, Yan, Long, Yuliang et al.2025 · 3 citationsOptics express. 2025;33(11):23907-23925
Accurate Patient Alignment without Unnecessary Imaging Dose via Synthesizing Patient-specific 3D CT Images from 2D kV Images2405.19338v1 · Yuzhen Ding, Jason M. Holmes, Hongying Feng et al.2024 · 7 citationsCommunications Medicine 4, Article number: 241 (2024)
X-Driver: Explainable Autonomous Driving with Vision-Language Models2505.05098v2 · Wei Liu, Jiyuan Zhang, Binxiong Zheng et al.2025 · 1 citationarXiv
A novel deep learning model based on YOLOv5 optimal method for coal gangue image recognition.40436918 · Gu, Tongkai, Zhao, Haiyan, Chang, Yasheng et al.2025 · 5 citationsScientific reports. 2025;15(1):18630
Modeling Spatial Patterns of Shapes.21132063 · Srivastava, Anuj, Liu, Wei, Joshi, Shantanu H2025 · 1 citationProceedings. International Conference on Image Processing. 2008;2008:1144-1147
Theoretical Insights into Fine-Tuning Attention Mechanism: Generalization and Optimization2410.02247v3 · Xinhao Yao, Hongjin Qian, Xiaolin Hu et al.2024 · 3 citationsarXiv
A novel 3D lightweight model for COVID-19 lung CT Lesion Segmentation.40057358 · Yang, Jingdong, Huang, Shaoyu, Wang, Han et al.2025 · 5 citationsMedical engineering & physics. 2025;137:104297
Dual-energy CT extracellular volume fraction predicts tumor collagen ratio and possibly survival for inoperable pancreatic cancer patients.39922972 · Liu, Wei, Chen, Yi, Xie, Tiansong et al.2025 · 13 citationsEuropean radiology. 2025;35(3):1451-1463
Dual-domain Wasserstein Generative Adversarial Network with Hybrid Loss for Low-dose CT Imaging.39761646 · Zhou, Haichuan, Liu, Wei, Zhou, Yu et al.2025 · 1 citationPhysics in medicine and biology. 2025;70(2)
DialogGen: Multi-modal Interactive Dialogue System for Multi-turn Text-to-Image Generation2403.08857v3 · Minbin Huang, Yanxin Long, Xinchi Deng et al.2024 · 0 citationsarXiv
Memory Kernel Coupling Theory: Obtain Time Correlation Function from Higher-order Moments2407.01923v3 · Wei Liu, Yu Su, Yao Wang et al.2024 · 1 citationarXiv
IDOL: Instant Photorealistic 3D Human Creation from a Single Image2412.14963v2 · Yiyu Zhuang, Jiaxi Lv, Hao Wen et al.2024 · 31 citationsCVPR 2025
Master-Slave Deep Architecture for Top-K Multiarmed Bandits With Nonlinear Bandit Feedback and Diversity Constraints.37999964 · Huang, Hanchi, Shen, Li, Ye, Deheng et al.2025 · 0 citationsIEEE transactions on neural networks and learning systems. 2024;35(12):17608-17619
Learnable Central Similarity Quantization for Efficient Image and Video Retrieval.38090871 · Yuan, Li, Wang, Tao, Zhang, Xiaopeng et al.2025 · 14 citationsIEEE transactions on neural networks and learning systems. 2024;35(12):18717-18730
Fast and Accurate Antibody Sequence Design via Structure Retrieval2502.19395v1 · Xingyi Zhang, Kun Xie, Ningqiao Huang et al.2025 · 0 citationsarXiv
Enhancing RAG with Active Learning on Conversation Records: Reject Incapables and Answer Capables2502.09073v1 · Xuzhao Geng, Haozhao Wang, Jun Wang et al.2025 · 0 citationsarXiv
Small-area marks realize nanoscale lithography alignment by a spatial and frequency domain fusion neural network.39951735 · Long, Yuliang, Tang, Yan, Jiang, Jinfeng et al.2025 · 4 citationsOptics letters. 2025;50(4):1089-1092
LUPET: Incorporating Hierarchical Information Path into Multilingual ASR2401.03689v3 · Wei Liu, Jingyong Hou, Dong Yang et al.2024 · 2 citationsarXiv
Head-to-head comparison of contrast-enhanced CT, dual-layer spectral-detector CT, and Gd-EOB-DTPA-enhanced MR in detecting neuroendocrine tumor liver metastases.39241307 · Xie, Tiansong, Liu, Wei, Chen, Lei et al.2024 · 2 citationsEuropean journal of radiology. 2024;181:111710
Wasserstein Discriminant Dictionary Learning for Graph Representation.38837929 · Zhang, Tong, Liu, Guangbu, Cui, Zhen et al.2024 · 1 citationIEEE transactions on pattern analysis and machine intelligence. 2024;46(12):8619-8635
RopeTP: Global Human Motion Recovery via Integrating Robust Pose Estimation with Diffusion Trajectory Prior2410.20358v2 · Mingjiang Liang, Yongkang Cheng, Hualin Liang et al.2024 · 4 citationsarXiv
A rate of penetration (ROP) prediction method based on improved dung beetle optimization algorithm and BiLSTM-SA.39468121 · Xiong, Mengyuan, Zheng, Shuangjin, Liu, Wei et al.2024 · 13 citationsScientific reports. 2024;14(1):25856
A Unified Analysis of AdaGrad With Weighted Aggregation and Momentum Acceleration.37310828 · Shen, Li, Chen, Congliang, Zou, Fangyu et al.2024 · 32 citationsIEEE transactions on neural networks and learning systems. 2024;35(10):14482-14490
PMSS: Pretrained Matrices Skeleton Selection for LLM Fine-tuning2409.16722v1 · Qibin Wang, Xiaolin Hu, Weikai Xu et al.2024 · 1 citationarXiv
SX-Stitch: An Efficient VMS-UNet Based Framework for Intraoperative Scoliosis X-Ray Image Stitching2409.05681v1 · Yi Li, Heting Gao, Mingde He et al.2024 · 3 citationsarXiv
Visualizing Spatial Semantics of Dimensionally Reduced Text Embeddings2409.03949v1 · Wei Liu, Chris North, Rebecca Faust2024 · 1 citationarXiv
Causality-Invariant Interactive Mining for Cross-Modal Similarity Learning.38512731 · Yan, Jiexi, Deng, Cheng, Huang, Heng et al.2024 · 32 citationsIEEE transactions on pattern analysis and machine intelligence. 2024;46(9):6216-6230
Sequential Manipulation Against Rank Aggregation: Theory and Algorithm2407.01916v1 · Ke Ma, Qianqian Xu, Jinshan Zeng et al.2024 · 5 citationsarXiv
GridFormer: Residual Dense Transformer with Grid Structure for Image Restoration in Adverse Weather Conditions2305.17863v2 · Tao Wang, Kaihao Zhang, Ziqian Shao et al.2023 · 211 citationsarXiv
Detecting Complex Multi-step Attacks with Explainable Graph Neural Network2405.11335v2 · Wei Liu, Peng Gao, Haotian Zhang et al.2024 · 1 citationarXiv
Docs2KG: Unified Knowledge Graph Construction from Heterogeneous Documents Assisted by Large Language Models2406.02962v1 · Qiang Sun, Yuanyi Luo, Wenxiao Zhang et al.2024 · 4 citationsarXiv
Large Span Sizes and Irregular Shapes Target Detection Methods Using Variable Convolution-Improved YOLOv8.38676177 · Gao, Yan, Liu, Wei, Chui, Hsiang-Chen et al.2024 · 12 citationsSensors (Basel, Switzerland). 2024;24(8)
Career total: 1357 works. 340 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.