28 citations · 61 across the 14 of their papers we have counts for
4 papers · 1 filter
Representation-Space MMD for Diffusion Language Models
Ilya Drobyshevskiy, Ilia Sudakov, Maksim Semenov +7
We introduce a post-training method for diffusion language models (DLMs) that minimizes Maximum Mean Discrepancy (MMD) between generated and reference distributions in the feature…
Registers Matter for Pixel-Space Diffusion Transformers
Nikita Starodubcev, Ilia Sudakov, Ilya Drobyshevskiy +2
Vision Transformers (ViTs) are known to exhibit high-norm patch-token outliers that degrade feature map quality, a problem effectively mitigated by register tokens. As diffusion mo…
Revisiting Autoregressive Models for Generative Image Classification
Ilia Sudakov, Artem Babenko, Dmitry Baranchuk
Class-conditional generative models have emerged as accurate and robust classifiers, with diffusion models demonstrating clear advantages over other visual generative paradigms, in…
Rethinking Global Text Conditioning in Diffusion Transformers
Nikita Starodubcev, Daniil Pakhomov, Zongze Wu +6
Diffusion transformers typically incorporate textual information via attention layers and a modulation mechanism using a pooled text embedding. Nevertheless, recent approaches disc…