AI RESEARCH

TAG: Tangential Amplifying Guidance for Hallucination-Resistant Sampling

arXiv CS.CV

ArXi:2510.04533v2 Announce Type: replace 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