3 papers
cs.LG2025
Demystifying Diffusion Objectives: Reweighted Losses are Better Variational Bounds
Jiaxin Shi, Michalis K. Titsias
We derive a new theoretical interpretation of the reweighted losses that are widely used for training diffusion models. Our method is based on constructing a cascade of time-depend…
stat.ML2025
Self-Speculative Masked Diffusions
Andrew Campbell, Valentin De Bortoli, Jiaxin Shi +1
We present self-speculative masked diffusions, a new class of masked diffusion generative models for discrete data that require significantly fewer function evaluations to generate…
cs.LG2025
Learning-Order Autoregressive Models with Application to Molecular Graph Generation
Zhe Wang, Jiaxin Shi, Nicolas Heess +2
Autoregressive models (ARMs) have become the workhorse for sequence generation tasks, since many problems can be modeled as next-token prediction. While there appears to be a natur…