Steepest Guidance: A Practical and Principled Approach to Inference-Time Alignment of Flow and Diffusion-based Models
arXiv:2609.39091v1 Announce Type: new Abstract: Inference-time alignment of flow and diffusion-based models is critical for achieving flexible generative modeling. Theoretically, Doob's $h$-transform provides an elegant solution to this problem, and most existing methods are based on this principle…
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-10-01 04:00 · arXiv stat.ML
Steepest Guidance: A Practical and Principled Approach to Inference-Time Alignment of Flow and Diffusion-based Models