Justin Deschenaux

Partition Generative Modeling: Masked Modeling Without Masks

The Diffusion Duality, Chapter II: $\Psi$-Samplers and Efficient Curriculum

Loopholing Discrete Diffusion: Deterministic Bypass of the Sampling Wall

Beyond Autoregression: Fast LLMs via Self-Distillation Through Time

One-Step is Enough: Sparse Autoencoders for Text-to-Image Diffusion Models

The Diffusion Duality

Unpacking SDXL Turbo: Interpreting Text-to-Image Models with Sparse Autoencoders