{"ID":2837459,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.18942","arxiv_id":"2511.18942","title":"VeCoR -- Velocity Contrastive Regularization for Flow Matching","abstract":"Flow Matching (FM) has recently emerged as a principled and efficient alternative to diffusion models. Standard FM encourages the learned velocity field to follow a target direction; however, it may accumulate errors along the trajectory and drive samples off the data manifold, leading to perceptual degradation, especially in lightweight or low-step configurations. To enhance stability and generalization, we extend FM into a balanced attract-repel scheme that provides explicit guidance on both \"where to go\" and \"where not to go.\" To be formal, we propose \\textbf{Velocity Contrastive Regularization (VeCoR)}, a complementary training scheme for flow-based generative modeling that augments the standard FM objective with contrastive, two-sided supervision. VeCoR not only aligns the predicted velocity with a stable reference direction (positive supervision) but also pushes it away from inconsistent, off-manifold directions (negative supervision). This contrastive formulation transforms FM from a purely attractive, one-sided objective into a two-sided training signal, regularizing trajectory evolution and improving perceptual fidelity across datasets and backbones. On ImageNet-1K 256$\\times$256, VeCoR yields 22\\% and 35\\% relative FID reductions on SiT-XL/2 and REPA-SiT-XL/2 backbones, respectively, and achieves further FID gains (32\\% relative) on MS-COCO text-to-image generation, demonstrating consistent improvements in stability, convergence, and image quality, particularly in low-step and lightweight settings. Project page: https://p458732.github.io/VeCoR_Project_Page/","short_abstract":"Flow Matching (FM) has recently emerged as a principled and efficient alternative to diffusion models. Standard FM encourages the learned velocity field to follow a target direction; however, it may accumulate errors along the trajectory and drive samples off the data manifold, leading to perceptual degradation, especi...","url_abs":"https://arxiv.org/abs/2511.18942","url_pdf":"https://arxiv.org/pdf/2511.18942v2","authors":"[\"Zong-Wei Hong\",\"Jing-lun Li\",\"Lin-Ze Li\",\"Shen Zhang\",\"Yao Tang\"]","published":"2025-11-24T09:48:38Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false}