Flow matching models follow a two-stage process of navigation across data modes then refinement to nearest samples, revealed by exact computation of the oracle marginal velocity field.
Deep unsupervised learning using nonequilibrium thermodynamics
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
AdaScope adaptively selects optimal RL intervention points during diffusion denoising by monitoring structural and semantic changes, delivering 66% higher performance at 59% lower cost than full-trajectory RL baselines.
A quantization technique for diffusion models that aligns sampling trajectories to preserve high-order sampler performance under quantization noise.
citing papers explorer
-
From Navigation to Refinement: Revealing the Two-Stage Nature of Flow-based Diffusion Models through Oracle Velocity
Flow matching models follow a two-stage process of navigation across data modes then refinement to nearest samples, revealed by exact computation of the oracle marginal velocity field.
-
Do Less, Achieve More: Do We Need Every-Step Optimization for RL Fine-tuning of Diffusion Models?
AdaScope adaptively selects optimal RL intervention points during diffusion denoising by monitoring structural and semantic changes, delivering 66% higher performance at 59% lower cost than full-trajectory RL baselines.
-
Sampling-Aware Quantization for Diffusion Models
A quantization technique for diffusion models that aligns sampling trajectories to preserve high-order sampler performance under quantization noise.