Aug 2026· Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2· pp. 3691-3702· 0 citations· 22 references
TL;DR
Low-Rank Prior-Induced Consistency Flow Matching (LOFT) is proposed for efficient and effective distribution modeling under highly sparse data, and introduces an uncertainty-aware rectification mechanism to enable efficient inference by linearizing generative trajectories.
Abstract
Generative models like diffusion and flow matching excel in traffic imputation but suffer from high inference latency, as the learned vector fields typically induce curved generative trajectories requiring multi-step numerical integration. Furthermore, learning the transformation from non-informative priors introduces redundant computational overhead. To address these issues, we propose Low-Rank Prior-Induced Consistency Flow Matching (LOFT) for efficient and effective distribution modeling under highly sparse data. First, we construct a low-rank prior from sparse observations to recover inherent spatiotemporal correlations. Initializing the flow with this informative prior reduces the mapping complexity, allowing the model to focus on fine-grained variations. Second, to enable efficient inference by linearizing generative trajectories, we introduce an uncertainty-aware rectification mechanism. This mechanism resolves the gradient conflict between improving accuracy and trajectory linearization by dynamically arbitrating the optimization trade-off based on the training progress and data uncertainty. Experimental results demonstrate that LOFT surpasses state-of-the-art baselines using an NFE (Number of Function Evaluations) of 2, whereas competing methods typically require 20 to 50 NFE, achieving over a 10× improvement in inference efficiency. The code is available at https://github.com/maoxiaowei97/LOFT.
This work introduces a novel framework, Gaussian Bridge Consistency (GBC), to address challenges of semi-supervised learning by constructing semantic interpolation paths between unlabeled samples and high-quality class anchors, and proposes BridgeMix, a confidence-aware feature mixing strategy that interpolates both sample and anchor pairs to amplify cross-sample generalization.
Hong-Yang He, Xin-Yuan Song, Yan Zhong et al.· 0 citations
Incomplete Multi-View Clustering addresses the problem of clustering multi-modal data when certain views are missing. Recent end-to-end generative approaches leverage diffusion models to recover missing views via stochastic noise-to-data trajectories. While expressive, such mechanisms are not explicitly designed for clustering, as they initialize from cluster-agnostic noise and rely on stochastic denoising dynamics. In this work, we revisit probability path design in end-to-end generative IMVC. We introduce a flow-matching framework with a linear interpolation path between paired view representations, that replaces diffusion with probability flows between observed and missing views. We provide a formal analysis showing that deterministic ODE flows are inherently better aligned with clustering objectives than diffusion-based stochastic trajectories, especially in terms of transport mechanisms that respect class-conditional data distributions and maintain cluster consistency in finite-step regimes. Building upon this insight, we develop an end-to-end IMVC architecture that integrates straight-path flow-matching view completion with cluster-level and entropy-based alignment to enforce cross-view clustering consistency. Extensive experiments on standard IMVC benchmarks demonstrate that the proposed framework establishes new state-of-the-art performance.
Yiteng Yuan, Junyan Wang, Zheyuan Liu et al.· 0 citations
The decomposition provides a theoretical basis for adapting likelihood-based LLM methods to flow matching, while distinguishing exact substitutions from controlled surrogates, while distinguishing exact substitutions from controlled surrogates.
High-fidelity image generation faces a trade-off between speed and quality. Diffusion models produce strong visuals but require costly iterative sampling. Existing efficient methods mainly distill pretrained models into few-step samplers, a challenging process that depends heavily on teacher-model quality. In this paper, we introduce XYZFlow, a framework that rethinks efficient generation through multidimensional scaling of flow matching. Unlike single-step mappings, XYZFlow enhances expressivity by making probability paths more identifiable and learnable through structured multidimensional conditioning. We view autoregressive modeling as implicit flow straightening, where richer context reduces trajectory ambiguity. XYZFlow realizes this idea through two orthogonal dimensions: temporal scaling, which uses non-Markovian conditioning on the full denoising history; and spatial scaling, enabled by Next Shortcut Prediction, which sequentially generates patches using preceding patches'denoising trajectories as priors. Experiments show that XYZFlow achieves state-of-the-art performance, with 7.2-8.5X teacher speedups and competitive FID, while Next Shortcut Prediction delivers superior quality-latency trade-offs over model scaling or step reduction.
Jinxiu Liu, Xuan Liu, Kangfu Mei et al.· 0 citations
This work empirically demonstrates that the uncertainty over the value of each token is closely related to the density of available context in its neighborhood, and proposes a simple modification to the underlying continuous-time Markov chain (CTMC) that incorporates local context information.
D. Cherniavskii, Daniel Severo, Karen Ullrich· arXiv.org· 0 citations
Diffusion and flow-matching models dominate conditional image generation, yet inference-time scaling for these models is far less developed than for autoregressive language models. Because final quality is highly sensitive to the initial noise seed, many approaches spend extra compute on seed search or resampling under a black-box reward, but typically maintaining a constant memory footprint throughout inference. We show that relaxing this constraint enables an underexplored inference-time scaling axis: by front-loading exploration, evaluating many seeds early, and pruning aggressively, we can use a fixed compute budget more effectively. \emph{Progressive Seed Pruning} (\PSP) scores intermediate denoised estimates and progressively narrows the candidate set so that only promising trajectories are fully denoised, while keeping the total number of model evaluations fixed. Across diffusion and flow-matching backbones, \PSP \ consistently improves reward-guided selection and achieves higher GenEval scores (automated) and better human evaluation on prompt-alignment than best-of-$N$, importance-sampling, and tree-search baselines at matched compute. Project page: https://www.vision.caltech.edu/psp. Code: https://github.com/rogerioagjr/psp.
Rogério Guimarães, Pietro Perona· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
