TAG: Tangential Amplifying Guidance for Hallucination-Resistant Sampling

arXiv:2510.04533v2 Announce Type: replace Abstract: Diffusion models achieve state-of-the-art image generation but often produce semantic inconsistencies, or hallucinations. Existing inference-time guidance methods rely on external signals or architectural modifications, adding computational overhead. We propose mathbf{T}angential mathbf{A}mplifying mathbf{G}uidance mathbf{(TAG)}, a training-free, architecture-agnostic, plug-and-play guidance method that operates purely on trajectory signals. TAG uses an intermediate sample as a projection basis and amplifies the tangential components of the estimated score to correct the sampling trajectory. A first-order Taylor analysis shows that this steers the state toward higher-probability regions of the data manifold, reducing inconsistencies and improving fidelity while adding negligible overhead to existing samplers. Code is available at our Project Page (https://hyeon-cho.github.io/TAG/).

Source: arXiv cs.CV | 2026-05-27