From the 1 of 9 linked papers with an AI index.
9 papers
Retrofitting Linear Attention into Diffusion Language Models
Jinha Kim, Younghun Roh, Jaeyeon Kim
Diffusion language models (dLLMs) offer a promising alternative to autoregressive models by accelerating inference through parallel decoding. Recent dLLMs commonly use blockwise se…
From Interface to Inference: Eliciting Any-Order Inference from Any-Order Models
Seunggeun Kim, Jaeyeon Kim, Taekyun Lee +4
The paper investigates how to give language models a native ability to reason and generate text in any order, introducing insertion‑based and latent‑space masked diffusion methods…
Stop Training for the Worst: Progressive Unmasking Accelerates Masked Diffusion Training
Jaeyeon Kim, Jonathan Geuter, David Alvarez-Melis +2
Masked Diffusion Models (MDMs) have emerged as a promising approach for generative modeling in discrete spaces. By generating sequences in any order and allowing for parallel decod…
Fine-Tuning Masked Diffusion for Provable Self-Correction
Jaeyeon Kim, Seunggeun Kim, Taekyun Lee +4
A natural desideratum for generative models is self-correction--detecting and revising low-quality tokens at inference. While Masked Diffusion Models (MDMs) have emerged as a promi…
Delta Rectified Flow Sampling for Text-to-Image Editing
Gaspard Beaudouin, Minghan Li, Jaeyeon Kim +2
We propose Delta Rectified Flow Sampling (DRFS), a novel inversion-free, path-aware editing framework within rectified flow models for text-to-image editing. DRFS is a distillation…
Selective Underfitting in Diffusion Models
Kiwhan Song, Jaeyeon Kim, Sitan Chen +3
Diffusion models have emerged as the principal paradigm for generative modeling across various domains. During training, they learn the score function, which in turn is used to gen…