4 papers
From Next-Token to Next-Block: A Principled Adaptation Path for Diffusion LLMs
Yuchuan Tian, Yuchen Liang, Shuo Zhang +10
Diffusion Language Models (DLMs) enable fast generation, yet training large DLMs from scratch is costly. As a practical shortcut, adapting off-the-shelf Auto-Regressive (AR) model…
Deferred Commitment Decoding for Diffusion Language Models
Yingte Shu, Yuchuan Tian, Chao Xu +2
Diffusion language models (DLMs) have recently emerged as a strong alternative to autoregressive models by enabling parallel text generation. To improve inference efficiency and KV…
U-REPA: Aligning Diffusion U-Nets to ViTs
Yuchuan Tian, Hanting Chen, Mengyu Zheng +3
Representation Alignment (REPA) that aligns Diffusion Transformer (DiT) hidden-states with ViT visual encoders has proven highly effective in DiT training, demonstrating superior c…
Instruct-IPT: All-in-One Image Processing Transformer via Weight Modulation
Yuchuan Tian, Jianhong Han, Hanting Chen +5
Due to the unaffordable size and intensive computation costs of low-level vision models, All-in-One models that are designed to address a handful of low-level vision tasks simultan…