TailSteer: Trajectory-Tail Steering for Drift-Resistant Multi-turn Image Editing

TailSteer, a final-stage training framework, reduces cumulative visual drift in multi-turn editing by keeping early denoising dynamics close to the base model and learning tail-focused preservation corrections from on-policy rollouts, preserving pretrained generative and editing abilities.

Strong single-turn editing performance does not guarantee reliable multi-turn interaction: as edited outputs are repeatedly reused, small unintended changes can accumulate into severe visual drift. This long-term drift is often mitigated through training on multi-turn data or cross-turn rollouts, potentially altering pretrained priors, or through specialized inference-time mechanisms that are difficult to scale to foundation models. We introduce TailSteer, a final-stage training framework that improves multi-turn robustness while retaining the generative and editing capabilities acquired through earlier training. TailSteer follows a simple principle: keep early denoising dynamics close to…

Upvotes

28

Authors

9

Published

Nov 4, 2026

arXiv

arXiv abstract

Code

Lyricccco/tailsteer

Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.