Showing stat.MLShow all
2 papers · 1 filter
stat.ML2026
A Quantitative Approximation Framework for Flow Distillation in Diffusion Models
Weiguo Gao, Ming Li, Lei Shi +1
We develop a quantitative framework for diffusion distillation by viewing few step sampling as approximation through compositions of learned flow maps. For trajectory distillation…
stat.ML2026
Efficient Approximation for Encoder--Decoder Neural Operators via Variation Spaces
Jia-Qi Yang, Lei Shi
We study operator learning using encoder--decoder neural networks. Inspired by the function-space theory of neural networks, we introduce a variation space as an infinite-dimension…