collaborators

10 papers

cs.LG2026

BlockGen: Flexible Blockwise Sequence Modeling with Hybrid Samplers

Justin Deschenaux, Caglar Gulcehre

Is the uniform-state diffusion framework a more powerful paradigm for discrete diffusion? Recent studies indicate that this may be the case. In combination with predictor-corrector…

cs.LG2026

Language Modeling with Hyperspherical Flows

Justin Deschenaux, Caglar Gulcehre

Discrete Diffusion Language Models progressed rapidly as an alternative to autoregressive (AR) models, motivated by their parallel generation abilities. However, for tractability,…

cs.LG2026

Fixed-Point Masked Generative Modeling

Andrea Miele, Yiming Qin, Alba Carballo-Castro +2

Masked Generative Models (MGMs) enable parallel decoding and achieve strong performance across modalities, but require full-sequence bidirectional transformers at every step, makin…

cs.LG2026

The Diffusion Duality, Chapter II: -Samplers

Justin Deschenaux, Caglar Gulcehre, Subham Sekhar Sahoo

Uniform-state discrete diffusion models excel at few-step generation and guidance due to their ability to self-correct, making them preferred over autoregressive or Masked diffusio…

cs.LG2026

Loopholing Discrete Diffusion: Deterministic Bypass of the Sampling Wall

Mingyu Jo, Jaesik Yoon, Justin Deschenaux +2

Discrete diffusion models offer a promising alternative to autoregressive generation through parallel decoding, but they suffer from a sampling wall: once categorical sampling occu…

cs.LG2026

Partition Generative Modeling: Masked Modeling Without Masks

Justin Deschenaux, Lan Tran, Caglar Gulcehre

Masked generative models (MGMs) can generate tokens in parallel and in any order, unlike autoregressive models (ARMs), which decode one token at a time, left-to-right. However, MGM…