cs.CVOct 30, 2026

TACO: Trajectory-Aware Curvature Observation for Memorization Localization and Mitigation in Diffusion Models

Authors: Ruxi Gu, Zilei Wang, Wei Wang

Organizations: Department of Automation, University of Science and Technology of China · State Key Laboratory of General Artificial Intelligence, BIGAI · School of Computer and Communication Engineering, University of Science and Technology Beijing

Abstract

Text-to-image diffusion models can reproduce memorized training content within localized image regions, making precise localization essential for targeted mitigation. However, curvature observations at a single denoising state can contain transient responses, while spatially uniform mitigation may disrupt prompt-relevant content. We present Trajectory-Aware Curvature Observation (TACO), a unified framework for local memorization detection and mitigation in diffusion models. Our empirical analysis reveals that memorization-related curvature becomes pronounced during late-stage denoising and persists at consistent spatial locations across neighboring states. Motivated by these observations, TACO aggregates prompt-dependent curvature responses along the late denoising trajectory and applies latent-guided spatial refinement to improve spatial coherence. The resulting memorization map serves both as a localization signal and as a spatial control signal for mitigation. Specifically, TACO uses this map to steer existing inference-time interventions toward memorization-related regions through spatial reweighting and localized guidance correction. Extensive experiments demonstrate that TACO consistently outperforms competing localization methods and improves the Pareto trade-off between memorization suppression and generation quality. These results establish trajectory-aware spatial analysis as an effective link between memorization localization and targeted mitigation.

Figures & tables

Appendix figures & tables8 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Localizing Memorized Regions in Diffusion Models via Coordinate-Wise Curvature Differences

    May 26, 2026Gwangho Kim, Sungyoon LeeMemorization in Generative ModelsDiffusion Models

  2. Steering Away from Memorization: Reachability-Constrained Reinforcement Learning for Text-to-Image Diffusion

    Feb 24, 2026Sathwik Karnik, Juyeop Kim, Sanmi Koyejo +2Memorization in Generative ModelsT2I Diffusion Models

  3. Valid Early Detection of Memorization in Diffusion Models

    Oct 25, 2026Yixiao Jing, Chia-Yu Hsu, Milad Hoseinpour +1Memorization in Generative ModelsSequential Hypothesis Testing