6 papers
CANDI: Hybrid Discrete-Continuous Diffusion Models
Patrick Pynadath, Jiaxin Shi, Ruqi Zhang
While continuous diffusion has shown remarkable success in continuous domains such as image generation, its direct application to discrete data has underperformed pure discrete for…
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…
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…
Informed Correctors for Discrete Diffusion Models
Yixiu Zhao, Jiaxin Shi, Feng Chen +3
Discrete diffusion has emerged as a powerful framework for generative modeling in discrete domains, yet efficiently sampling from these models remains challenging. Existing samplin…
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…
Simplified and Generalized Masked Diffusion for Discrete Data
Jiaxin Shi, Kehang Han, Zhe Wang +2
Masked (or absorbing) diffusion is actively explored as an alternative to autoregressive models for generative modeling of discrete data. However, existing work in this area has be…