| title | MT Forcing: Towards Stable and Consistent Multi-Turn Image Editing with Autoregressive Diffusion |
|---|---|
| authors | Houyuan Chen, Fanzhou Wang, Xiangyu Fan, Zesong Qiu, Yukun Wei, Songlin Yang, Zhitao Yang, Lvmin Zhang, Pei Yang, Hao Zhao, Lei Yang, Anyi Rao |
| date | 2026-10-18 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2610.25404 |
| affiliation | SenseNova |
| upvotes | 44 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | Multi-turn image editing aims to modify an image according to a sequence of instructions, enabling more effective interactive visual content creation for users. However, existing methods often exhibit noticeable drift after only a few editing turns, manifesting in two aspects: 1) unstable visual quality, with accumulating artifacts and degraded details; and 2) inconsistent image content, with unintended changes to preserved regions and prior edits. To address these challenges, we propose MT Forcing, a novel training paradigm for multi-turn image editing with unified multimodal models (UMMs) based on autoregressive diffusion. Specifically, we propose Single-Turn Distribution Matching Distillation (Single-Turn DMD), which supervises student self-rollouts with a teacher that applies cumulative edits to the source image in a single turn, providing visual-quality guidance without recursive error accumulation. Additionally, we introduce Teacher-Forcing Guidance, which supervises history-dependent transitions on reference trajectories during warmup and as a regularizer during distillation, encouraging cross-turn content consistency beyond what per-turn distribution matching alone can ensure. Extensive experiments demonstrate that our approach significantly improves the multi-turn image editing capabilities of UMMs, yielding more stable visual quality and stronger cross-turn consistency. |
cite
@misc{chen2026mt,
title={MT Forcing: Towards Stable and Consistent Multi-Turn Image Editing with Autoregressive Diffusion},
author={Houyuan Chen and Fanzhou Wang and Xiangyu Fan and Zesong Qiu and Yukun Wei and Songlin Yang and Zhitao Yang and Lvmin Zhang and Pei Yang and Hao Zhao and Lei Yang and Anyi Rao},
year={2026},
eprint={2610.25404},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2610.25404}
}