Empirical flow matching introduces coupled biases from plug-in estimation, including altered statistical targets, non-gradient minimizers, and non-unique dynamics via flux-null fields, with base distribution controlling kinetic energy tails.
Entropic time schedulers for generative diffusion models.arXiv preprint arXiv:2504.13612, 2025
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
Continuous flows on token embeddings with flow-map distillation produce one-step language models whose quality exceeds recent 8-step discrete diffusion baselines on LM1B and OpenWebText.
citing papers explorer
-
On The Hidden Biases of Flow Matching Samplers
Empirical flow matching introduces coupled biases from plug-in estimation, including altered statistical targets, non-gradient minimizers, and non-unique dynamics via flux-null fields, with base distribution controlling kinetic energy tails.
-
Flow Map Language Models: One-step Language Modeling via Continuous Denoising
Continuous flows on token embeddings with flow-map distillation produce one-step language models whose quality exceeds recent 8-step discrete diffusion baselines on LM1B and OpenWebText.