Deschenaux, Justin

9 publications

ICLR 2026 Loopholing Discrete Diffusion: Deterministic Bypass of the Sampling Wall Mingyu Jo, Jaesik Yoon, Justin Deschenaux, Caglar Gulcehre, Sungjin Ahn

ICLR 2026 Partition Generative Modeling: Masked Modeling Without Masks Justin Deschenaux, Lan Tran, Caglar Gulcehre

ICLR 2026 The Diffusion Duality, Chapter II: $\Psi$-Samplers Justin Deschenaux, Caglar Gulcehre, Subham Sekhar Sahoo

ICLR 2025 Beyond Autoregression: Fast LLMs via Self-Distillation Through Time Justin Deschenaux, Caglar Gulcehre

NeurIPS 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

ICML 2025 The Diffusion Duality Subham Sekhar Sahoo, Justin Deschenaux, Aaron Gokaslan, Guanghan Wang, Justin T Chiu, Volodymyr Kuleshov

ICLRW 2025 The Diffusion Duality Subham Sekhar Sahoo, Justin Deschenaux, Aaron Gokaslan, Guanghan Wang, Justin T Chiu, Volodymyr Kuleshov

ICML 2024 Going Beyond Compositions, DDPMs Can Produce Zero-Shot Interpolations Justin Deschenaux, Igor Krawczuk, Grigorios Chrysos, Volkan Cevher

ICLR 2023 Distributed Extra-Gradient with Optimal Complexity and Communication Guarantees Ali Ramezani-Kebrya, Kimon Antonakopoulos, Igor Krawczuk, Justin Deschenaux, Volkan Cevher