The slow iterative sampling nature remains a major bottleneck for the practical deployment of diffusion and flow-based generative models. While consistency models (CMs) represent a state-of-the-art distillation-based approach for efficient generation, their large-scale application is still limited by two key issues: training instability and inflexible sampling. Existing methods seek to mitigate these problems through architectural adjustments or regularized objectives, yet overlook the critical reliance on trajectory selection. In this work, we first conduct an analysis on these two limitations: training instability originates from loss divergence induced by unstable self-supervised term, whereas sampling inflexibility arises from error accumulation. Based on these insights and analysis, we propose the Dual-End Consistency Model (DE-CM) that selects vital sub-trajectory clusters to achieve stable and effective training. DE-CM decomposes the PF-ODE trajectory and selects three critical sub-trajectories as optimization targets. Specifically, our approach leverages continuous-time CMs objectives to achieve few-step distillation and utilizes flow matching as a boundary regularizer to stabilize the training process. Furthermore, we propose a novel noise-to-noisy (N2N) mapping that can map noise to any point, thereby alleviating the error accumulation in the first step. Extensive experimental results show the effectiveness of our method: it achieves a state-of-the-art FID score of 1.70 in one-step generation on the ImageNet 256x256 dataset, outperforming existing CM-based one-step approaches.
Dual-Expert Consistency Model for Efficient and High-Quality Video Generation
Nanjing University(南京大学);The University of Hong Kong(香港大学);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);University of Chinese Academy of Sciences(中国科学院大学);S-Lab, Nanyang Technological University(南洋理工大学S实验室)
Multi-scale Latent Point Consistency Models for 3D Shape Generation
Wangxuan Institute of Computer Technology, Peking University(北京大学王轩计算机技术研究所);Department of Electrical and Computer Engineering, University of British Columbia(不列颠哥伦比亚大学电气与计算机工程系)
Dual-Space Modality Consistency Learning for Universal Cross-Modal Re-Identification
School of Artificial Intelligence, Beihang University(北京航空航天大学人工智能学院);School of Humanities and Social Sciences, Beihang University(北京航空航天大学人文与社会科学高等研究院);School of Computer Science and Engineering, Beihang University(北京航空航天大学计算机科学与工程学院);School of Informatics, Xiamen University(厦门大学信息学院)
Style-Hallucinated Dual Consistency Learning: A Unified Framework for Visual Domain Generalization
National University of Singapore(新加坡国立大学);Singapore University of Technology and Design(新加坡科技设计大学);University of Trento(特伦托大学);University of Nottingham(诺丁汉大学)
Dual Cross-image Semantic Consistency with Self-aware Pseudo Labeling for Semi-supervised Medical Image Segmentation
School of Biomedical Engineering & State Key Laboratory of Advanced Medical Materials and Devices, ShanghaiTech University(生物医学工程学院及先进医疗材料与器件国家重点实验室,上海科技大学);Lingang Laboratory(临港实验室);Department of Radiology, Stanford University(放射科,斯坦福大学)
Dual-scale Enhanced and Cross-generative Consistency Learning for Semi-supervised Medical Image Segmentation
PCA Laboratory(PCA实验室);School of Computer Science and Engineering, Nanjing University of Science and Technology(南京理工大学计算机科学与工程学院);School of Computer Science and Engineering, Southeast University(东南大学计算机科学与工程学院);Medical School, Nanjing University(南京大学医学院);National Institute of Healthcare Data Science at Nanjing University(南京大学国家医疗数据科学研究院);Institute of High Performance Computing, A*STAR(新加坡科技研究局高性能计算研究所)
Duala: Dual-Level Alignment of Subjects and Stimuli for Cross-Subject fMRI Decoding
State Key Laboratory of Novel Software Technology, Nanjing University(新型软件技术国家重点实验室,南京大学);Institute of Brain-Machine Interface, Nanjing University(脑机接口研究院,南京大学)
Iterating Consistency Models: Stability, Error Bounds and Noise Schedules
Université Paris Cité(巴黎西岱大学);CNRS(法国国家科学研究中心);Heriot-Watt University(赫瑞-瓦特大学);École Polytechnique(巴黎综合理工学院);EPITA(法国计算机科学与技术高等学院);Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学)
Deep Incomplete Multi-view Clustering with Distribution Dual-Consistency Recovery Guidance
School of Computer, National University of Defense Technology(国防科技大学计算机学院);Academy of Military Sciences(军事科学院);Chinese PLA General Hospital(中国人民解放军总医院)
Dual Consistent Constraint via Disentangled Consistency and Complementarity for Multi-view Clustering
College of Data Science and Application(数据科学与应用学院);Inner Mongolia Autonomous Region Engineering and Technology Research Center of Big Data-Based Software Service(内蒙古自治区大数据软件服务工程技术研究中心);Inner Mongolia Key Laboratory of Beijiang Cyberspace Security(内蒙古北疆网络空间安全重点实验室)
Dual-Consistency Semi-Supervised Learning with Uncertainty Quantification for COVID-19 Lesion Segmentation from CT Images
Imsight AI Research Lab(Imsight人工智能研究实验室);The Chinese University of Hong Kong(香港中文大学);The Hong Kong University of Science and Technology(香港科技大学);Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院)
Dual Agreement Consistency Learning for Semi-Supervised Fetal Ultrasound Segmentation
Research Ireland Centre for Research Training in Machine Learning(爱尔兰研究机器学习研究中心);School of Medicine, University College Dublin(都柏林大学医学院);School of Computer Science, University College Dublin(都柏林大学计算机科学学院);School of Computer Science and Digital Technologies, Aston University(阿斯顿大学计算机科学与数字技术学院)
BioD2C: A Dual-level Semantic Consistency Constraint Framework for Biomedical VQA
Shandong University(山东大学);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));Institute of Deep Perception Technology, JITRI(JITRI深度感知技术研究院)
Dual-Decoder Consistency via Pseudo-Labels Guided Data Augmentation for Semi-Supervised Medical Image Segmentation
Fuzhou University(福州大学);Fujian Medical University Union Hospital(福建医科大学附属协和医院);Fujian Medical Ultrasound Research Institute(福建省医学超声研究所);Macao Polytechnic University(澳门理工大学)
A coarse-to-fine framework for unsupervised multi-contrast MR image deformable registration with dual consistency constraint
Paul C. Lauterbur Research Center for Biomedical Imaging, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院保罗·C·劳特伯生物医学成像研究中心);Pengcheng Laboratory(鹏城实验室);Pazhou Lab(琶洲实验室);Guizhou Provincial People’s Hospital(贵州省人民医院)
A Self-ensembling Framework for Semi-supervised Knee Cartilage Defects Assessment with Dual-Consistency
Institute for Medical Imaging Technology, School of Biomedical Engineering, Shanghai Jiao Tong University(上海交通大学医学院生物医学工程学院医学影像技术研究所);Shanghai United Imaging Intelligence Co., Ltd.(上海联影智能科技有限公司);Department of Imaging, Tongren Hospital, Shanghai Jiao Tong University School of Medicine(上海交通大学医学院附属同仁医院影像科)
Self-Evolving Spatial Reasoning in Vision Language Models via Geometric Logic Consistency
Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);The City University of New York(纽约城市大学);The Chinese University of Hong Kong(香港中文大学);Data61 CSIRO(Data61澳大利亚国家科学研究院);University of New South Wales(新南威尔士大学);Australian National University(澳大利亚国立大学)
Cognitive Dual-Process Planning for Autonomous Driving with Structured Scene Knowledge and Verifiable Reasoning-Action Consistency
School of Mechanical Engineering, Beijing Institute of Technology(北京理工大学机械工程学院);National Engineering Research Center of Electric Vehicles, Beijing Institute of Technology(北京理工大学电动车辆国家工程研究中心);School of Mechanical Engineering, Southeast University(东南大学机械工程学院)