View a PDF of the paper titled Friction-Augmented Drifting Models for Resource-Efficient Domain Translation, by Arkadii Kazanskii and 5 other authors
Abstract:Drifting Models (DMs) train a one-step generator by regressing its output towards a target displaced by a kernel drift. DMF (Drifting Model with Friction) scales this displacement linearly from full drift to zero. With plain gradient descent, scaling the drift gives the same updates as linear learning-rate decay. With Adam, it also changes the gradient moments. For a constant multiplier $c>0$, its effect in exact arithmetic is to replace Adam’s $\epsilon$ by $\epsilon/c$. In a two-particle model with unnormalised Laplace interactions, we derive the distance at which attraction balances repulsion. On FFHQ adult-to-child translation, DMF lowered FID and CMMD relative to fixed-rate DM in all five seed pairs. In a separate paired comparison, mean FID and CMMD were lower for DM with linear learning-rate decay than for DMF. Both 95% intervals for the paired differences included zero. DMF inherits DM’s low training cost. At batch size 32 on one RTX A6000, mean training times were 6.85 minutes for DMF, 6.93 for DM and 133.48 for Optimal Flow Matching (OFM). At this batch size, DMF also achieved lower FID and CMMD than OFM (paired $p=0.002$ and $0.021$, respectively).
Submission history
From: Tatiana Petrova [view email]
[v1]
Mon, 20 Apr 2026 12:47:27 UTC (7,878 KB)
[v2]
Fri, 14 Aug 2026 05:23:13 UTC (7,878 KB)
[v3]
Wed, 18 Nov 2026 23:39:28 UTC (8,154 KB)
![[2604.18194] Friction-Augmented Drifting Models for Resource-Efficient Domain Translation [2604.18194] Friction-Augmented Drifting Models for Resource-Efficient Domain Translation](https://techwavedispatch.com/wp-content/uploads/2026/11/260418194-Friction-Augmented-Drifting-Models-for-Resource-Efficient-Domain-Translation-1024x597.png)