Justin Deschenaux

According to our database, Justin Deschenaux authored at least 14 papers between 2023 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

Fixed-Point Masked Generative Modeling.

Andrea Miele, Yiming Qin, Alba Carballo-Castro, Justin Deschenaux, Pascal Frossard

CoRR, May, 2026

Language Modeling with Hyperspherical Flows.

Justin Deschenaux, Caglar Gulcehre

CoRR, May, 2026

The Diffusion Duality, Chapter II: Ψ-Samplers and Efficient Curriculum.

Justin Deschenaux, Caglar Gulcehre, Subham Sekhar Sahoo

CoRR, February, 2026

Scaling Beyond Masked Diffusion Language Models.

Subham Sekhar Sahoo, Jean-Marie Lemercier, Zhihan Yang, Justin Deschenaux, Jingyu Liu, John Thickstun, Ante Jukic

CoRR, February, 2026

2025

Loopholing Discrete Diffusion: Deterministic Bypass of the Sampling Wall.

Mingyu Jo, Jaesik Yoon, Justin Deschenaux, Caglar Gulcehre, Sungjin Ahn

CoRR, October, 2025

Partition Generative Modeling: Masked Modeling Without Masks.

Justin Deschenaux, Lan Tran, Caglar Gulcehre

CoRR, May, 2025

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

Viacheslav Surkov, Chris Wendler, Antonio Mari, Mikhail Terekhov, Justin Deschenaux, Robert West, Caglar Gulcehre, David Bau

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

The Diffusion Duality.

Subham Sekhar Sahoo, Justin Deschenaux, Aaron Gokaslan, Guanghan Wang, Justin T. Chiu, Volodymyr Kuleshov

Proceedings of the Forty-second International Conference on Machine Learning, 2025

Beyond Autoregression: Fast LLMs via Self-Distillation Through Time.

Justin Deschenaux, Caglar Gulcehre

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024

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

Viacheslav Surkov, Chris Wendler, Mikhail Terekhov, Justin Deschenaux, Robert West, Caglar Gulcehre

CoRR, 2024

Promises, Outlooks and Challenges of Diffusion Language Modeling.

Justin Deschenaux, Caglar Gulcehre

CoRR, 2024

Going beyond compositional generalization, DDPMs can produce zero-shot interpolation.

Justin Deschenaux, Igor Krawczuk, Grigorios Chrysos, Volkan Cevher

CoRR, 2024

Going beyond Compositions, DDPMs Can Produce Zero-Shot Interpolations.

Justin Deschenaux, Igor Krawczuk, Grigorios Chrysos, Volkan Cevher

Proceedings of the Forty-first International Conference on Machine Learning, 2024

2023

Distributed Extra-gradient with Optimal Complexity and Communication Guarantees.

Ali Ramezani-Kebrya, Kimon Antonakopoulos, Igor Krawczuk, Justin Deschenaux, Volkan Cevher

Proceedings of the Eleventh International Conference on Learning Representations, 2023