cs.LGFeb 4, 2026

Temporal Pair Consistency for Flow Matching

Authors: Chika Maduabuchi, Jindong Wang

Organizations: William & Mary.

Abstract

Flow-matching-style generative models learn time-dependent vector fields, but standard objectives supervise each timestep independently, leaving shared-path temporal structure unused. We introduce Temporal Pair Consistency (TPC), a simple training-time objective that couples velocity predictions at paired timesteps along the same probability path. TPC leaves the architecture, probability path, sampler, and inference-time computation unchanged. Under matched backbones, training budgets, solvers, and numbers of function evaluations, TPC improves sample quality across flow matching, OT-CFM, rectified flow, DiT-style backbones, and MeanFlow. On CIFAR-10, TPC improves FM from 6.35 to 3.19 FID and OT-CFM from 3.58 to 2.90 FID at the same NFE. Mechanism diagnostics show lower measured gradient variance, higher paired-gradient correlation, and reduced temporal roughness, while random and local pairing controls are substantially weaker. Higher-resolution ImageNet experiments further show consistent gains for DiT-XL/2 at 256 and 512 resolution and for MeanFlow at 256 resolution, all at matched inference cost.

Figures & tables

Explore similar work

CardsList
  1. Posterior Augmented Flow Matching

    May 1, 2026George Stoica, Sayak Paul, Matthew Wallingford +6Flow MatchingConditional Image Generation

  2. Learning Conditional Source Distribution via Flow Reversal for Temporal Flow Matching

    Oct 4, 2026Kuan-Hsun Tu, Hsuan-Chi Liu, Jia-Wei Liao +3Flow MatchingVideo Prediction