Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Discrete Meanflow Training Curriculum
Chia-Hong Hsu, Frank Wood
Flow-based image generative models exhibit stable training and produce high quality samples when using multi-step sampling procedures. One-step generative models can produce high q…
cs.LG2026
Post-Hoc Guidance for Consistency Models by Joint Flow Distribution Learning
Chia-Hong Hsu, Randall Balestriero
Classifier-free Guidance (CFG) lets practitioners trade-off fidelity against diversity in Diffusion Models (DMs). The practicality of CFG is however hindered by DMs sampling cost.…
cs.LG2024
Self-Correcting Self-Consuming Loops for Generative Model Training
Nate Gillman, Michael Freeman, Daksh Aggarwal +4
As synthetic data becomes higher quality and proliferates on the internet, machine learning models are increasingly trained on a mix of human- and machine-generated data. Despite t…