PrismFlow: Residual Dynamics for Flow Matching in Time-Series Generation
Zhejiang University, China(浙江大学,中国);Nanyang Technological University, Singapore(南洋理工大学,新加坡);I2R, Agency for Science, Technology and Research (A*STAR), Singapore(科技研究局(A*STAR)新加坡研究所,新加坡)
Junru Zhang, Lang Feng, Jinbo Wang, Xu Guo, Yucheng Wang, Han Yu, Min Wu, Yabo Dong, Duanqing Xu
Generating high-quality time-series data is challenging because real-world signals often exhibit multimodal patterns and multiscale dynamics, including oscillations and high-frequency variations. Flow Matching (FM) offers an efficient alternative to diffusion models, but practical implementations typically rely on a single finite-capacity global vector-field estimator. In such heterogeneous temporal distributions, distinct regimes may pass through nearby flow states while requiring incompatible conditional velocities. A monolithic estimator trained with the standard $\ell_2$ velocity-matching objective may therefore learn an overly smoothed approximation of the local transport field. This estimator-level smoothing can attenuate branch-specific dynamics, leading to spectral distortion and poor mode coverage. To address this, we propose PrismFlow, a new FM method with Koopman-inspired dynamical experts. Each expert learns residual corrections in a latent space where local nonlinear temporal evolution can be approximated by linear transitions. We further propose a confidence-aware Winner-Take-All (WTA) objective that updates only the expert best aligned with each sample while masking gradients to the others, encouraging mode-specific specialization. During sampling, the selected expert adds a residual dynamical correction to the global transport field, preserving FM stability while recovering fine-grained and high-frequency temporal structures. Across various benchmarks, PrismFlow effectively mitigates the spectral contraction in standard FM and achieves state-of-the-art performance, with a 15.6% gain in Context-FID and a 38.6% improvement in Discriminative Score, while remaining robust in low-data settings and effective for forecasting and imputation.
AREX: Affine-Residual Exponential Integrator for Few-Step Sampling in Flow Matching
KTH Royal Institute of Technology(瑞典皇家理工学院);Nordita(北欧理论物理研究所);Stockholm University(斯德哥尔摩大学);International Computer Science Institute(国际计算机科学研究所);Lawrence Berkeley National Laboratory(劳伦斯伯克利国家实验室)
Multi-Fidelity Flow Matching: Cascaded Refinement of PDE Solutions
Department of Computer Science, Florida State University(佛罗里达州立大学计算机科学系);Department of Materials Science and Engineering, Florida State University(佛罗里达州立大学材料科学与工程系);Hildebrand Department of Petroleum and Geosystems Engineering, The University of Texas at Austin(德克萨斯大学奥斯汀分校石油与地质系统工程系)
Physics-Constrained Fine-Tuning of Flow-Matching Models for Generation and Inverse Problems
German Research Center for Artificial Intelligence (DFKI)(德国人工智能研究中心);Department of Computer Science, University of Kaiserslautern–Landau (RPTU)(凯泽斯劳滕-兰道大学计算机科学系);Department of Mathematics, Imperial College London(伦敦帝国理工学院数学系)
Self-Consistent Generative Paths via Admissible Random Variational Transport
PCA Lab, Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education, 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高维信息智能感知与系统教育部重点实验室PCA实验室)
Accelerated training of deep learning surrogate models for surface displacement and flow, with application to MCMC-based history matching of CO2 storage operations
DataCupid: Stable Matching Repair for Training Data Acquisition with Delayed Feedback
University of Hong Kong(香港大学);National University of Singapore(新加坡国立大学);Guangming Laboratory(光明实验室);University of Science and Technology of China(中国科学技术大学)
EReLiFM: Evidential Reliability-Aware Residual Flow Meta-Learning for Open-Set Domain Generalization under Noisy Labels
Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院);Hunan University(湖南大学);KTH Royal Institute of Technology(皇家理工学院);RISE Research Institutes of Sweden(瑞典RISE研究机构);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);The Chinese University of Hong Kong(香港中文大学)