| title | Follow the Mean: Reference-Guided Flow Matching |
|---|---|
| authors | Pedro M. P. Curvo, Maksim Zhdanov, Floor Eijkelboom, Jan-Willem van de Meent |
| date | 2026-05-12 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2605.10302 |
| affiliation | Amsterdam Machine Learning Lab |
| upvotes | 2 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | Existing approaches to controllable generation typically rely on fine-tuning, auxiliary networks, or test-time search. We show that flow matching admits a different control interface: adaptation through examples. For deterministic interpolants, the velocity field is solely governed by a conditional endpoint mean; shifting this mean shifts the flow itself. This yields a simple principle for controllable generation: steer a pretrained model by changing the reference set it follows. We instantiate this idea in two forms. Reference-Mean Guidance is training-free: it computes a closed-form endpoint-mean correction from a reference bank and applies it to a frozen FLUX.2-klein (4B) model, enabling control of color, identity, style, and structure while keeping the prompt, seed, and weights fixed. Semi-Parametric Guidance amortizes the same idea through an explicit mean anchor and learned residual refiner, matching unconditional DiT-B/4 quality on AFHQv2 while allowing the reference set to be swapped at inference time. These results point to a broader direction: generative models that adapt through data, not parameter updates. |
cite
@misc{curvo2026follow,
title={Follow the Mean: Reference-Guided Flow Matching},
author={Pedro M. P. Curvo and Maksim Zhdanov and Floor Eijkelboom and Jan-Willem van de Meent},
year={2026},
eprint={2605.10302},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2605.10302}
}