Newton Matching for Generative Modeling: A Unified Framework for Fine-Tuning and Sampling
The paradigm from isolated losses to iterative optimization over canonical models: population minimizers of standard conditional matching for terminal densities and approximate updates and define critical-point consistency as vanishing tangential displacement if and only if $\rho=\pi$.
Ze-Yang Li, Yunan Wang, Paolo Giaretta et al.
· 0 citations