Justin Deschenaux

PhD Student in Machine Learning at

Publications and pre-prints

* indicates equal contribution

Partition Generative Modeling: Masked Modeling Without Masks
Justin Deschenaux, Lan Tran, Caglar Gulcehre
ArXiv preprint
[paper]
The Diffusion Duality
Subham Sekhar Sahoo, Justin Deschenaux, Aaron Gokaslan, Guanghan Wang, Justin T Chiu, Volodymyr Kuleshov
International Conference on Machine Learning (ICML) 2025
[paper | code | project]
Beyond Autoregression: Fast LLMs via Self-Distillation Through Time
Justin Deschenaux, Caglar Gulcehre
International Conference on Learning Representations (ICLR) 2025
[paper | code | project]
Unpacking SDXL Turbo: Interpreting Text-to-Image Models with Sparse Autoencoders
Viacheslav Surkov, Chris Wendler, Mikhail Terekhov, Justin Deschenaux, Robert West, Caglar Gulcehre
ArXiv preprint
[paper | code | project]
Promises, Outlooks and Challenges of Diffusion Language Modeling
Justin Deschenaux, Caglar Gulcehre
ArXiv preprint
[paper]
Going beyond Compositions, DDPMs Can Produce Zero-Shot Interpolations
Justin Deschenaux*, Igor Krawczuk*, Grigorios Chrysos, Volkan Cevher
International Conference on Machine Learning (ICML) 2024
[paper | code]
Distributed extra-gradient with optimal complexity and communication guarantees
Ali Ramezani-Kebrya*, Kimon Antonakopoulos*, Igor Krawczuk*, Justin Deschenaux*, Volkan Cevher
International Conference on Learning Representations (ICLR) 2023
[paper | code]