[Submitted on 4 Feb 2026 (v1), last revised 5 Nov 2026 (this version, v3)]
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.
Submission history
From: Chika Maduabuchi [view email]
[v1] Wed, 4 Feb 2026 00:05:21 UTC (1,111 KB)
[v2] Thu, 19 Feb 2026 21:20:28 UTC (2,653 KB)
[v3] Thu, 5 Nov 2026 20:15:21 UTC (7,263 KB)
