3 papers
cs.CL2026
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…
cs.CV2026
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…
cs.CV2026
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…