HOrIc&RRO7HrEs#uNl NB%6GDjxO2Y0

My name is Justin Deschenaux and I am a PhD student at . I am advised by Professor Caglar Gulcehre, and I work on diffusion language models, a blazingly fast, controllable, and principled way to generate text.

Google Scholar GitHub

Latest News

Jan. 2026
Partition Generative Modeling (PGM) and Loopholing Discrete Diffusion were accepted into ICLR 2026. PGM was awarded an oral presentation!
Nov. 2025
We started a reading group on discrete diffusion with Subham and Zhihan.
May. 2025
The Diffusion Duality was accepted at ICML 2025.
Jan. 2025
Self-Distillation Through Time was accepted at ICLR 2025.

Selected Work

Partition Generative Modeling: Masked Modeling Without Masks

PGMs partition tokens to parallelize decoding with massive latency gains.

Loopholing Discrete Diffusion: Deterministic Bypass of the Sampling Wall

Loopholing forwards latents, improving sample quality and boosting reasoning.