Michael S. Albergo
2 papers · Latest:
Statistical Machine Learning
A unified perspective on fine-tuning and sampling with diffusion and flow models
This paper unifies fine-tuning and sampling for diffusion/flow models using exponential tilting, revealing gradient variance properties and supporting adjoint-based methods.
2605.00229
Machine LearningDiscrete Tilt Matching
Discrete Tilt Matching (DTM) is a novel likelihood-free method for fine-tuning masked diffusion LLMs, improving performance on various tasks.
2604.18739
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.