cs.LGNov 14, 2026

Spectral Steering: Local Inverse Geometry for Frozen Diffusion Generators

Authors: Angelo Moroncelli, Alessandro Leanza, Loris Roveda

Organizations: University of Applied Sciences and Arts of Southern Switzerland (SUPSI), IDSIA · Universit`a della Svizzera italiana (USI) · Politecnico di Milano

Abstract

A frozen diffusion generator may need to change several output properties while preserving others. We study when guidance faithfully realizes such a structured request and whether local inverse correction improves its direction. Our account links this benefit to the interaction between the request and the objective-specific remaining-sampler Jacobian: conditioning alone is insufficient. Spectral steering combines a request-specific cosine-gain predictor with damped inverse correction and fixed-time relinearization for finite edits. Scalar nulls and matched-movement controls test the predicted mechanism. Across 8,923 instances in a retrospectively identified local regime, predicted and realized gains correlate at Spearman 0.79, versus -0.11 for condition number. Experiments span images, audio, robotics, and control and planning, including complex character motion generation. On 50 paired inpainting cases, four corrections improve unobserved-pixel PSNR over Adam by 3.25 dB at equal total derivative traversals. Together, the analysis and controls connect request-dependent geometry to directional gains and establish where these gains translate into downstream performance.

Figures & tables

Appendix figures & tables37 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Correcting Guided Diffusion Trajectories with Spectral Alignment

    Oct 2, 2026Gihoon Kim, Taesup KimDiffusion Model GuidanceDiffusion Sampling

  2. Spectral Guidance for Flexible and Efficient Control of Diffusion Models

    May 27, 2026Gabriel Moreira, Manuel Marques, João Paulo Costeira +1Diffusion Model GuidanceDiffusion Guidance

  3. General and Efficient Steering of Diffusion Models

    Feb 11, 2026Qingsong Wang, Mikhail Belkin, Yusu WangDiffusion Model GuidanceActivation Steering