LFM models exhibit stability to data reduction and capacity shrinkage that is tied to the flow matching objective, enabling reduced-data training and coarse-to-fine inference with over 2x speedup.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
citing papers explorer
-
Exploring and Exploiting Stability in Latent Flow Matching
LFM models exhibit stability to data reduction and capacity shrinkage that is tied to the flow matching objective, enabling reduced-data training and coarse-to-fine inference with over 2x speedup.
- DataComp-VLM: Improved Open Datasets for Vision-Language Models