Ilya Drobyshevskiy — accepted AI-conference papers

2026

Revisiting Global Text Conditioning in Diffusion Transformers

Nikita Starodubcev, Daniil Pakhomov, Zongze Wu, Ilya Drobyshevskiy, Yuchen Liu, Zhonghao Wang +3

ICLR 2026poster

Diffusion transformers typically incorporate textual information via (i) attention layers and (ii) a modulation mechanism using a pooled text embedding. Nevertheless, recent approaches discard modulation-based text conditioning and rely exclusively on attention. In this paper, we address whether mod…

Cited by 0 Source ↗code ↗Scholar ↗

2026

Scale-wise Distillation of Diffusion Models

Nikita Starodubcev, Ilya Drobyshevskiy, Denis Kuznedelev, Artem Babenko, Dmitry Baranchuk

ICLR 2026poster

Recent diffusion distillation methods have achieved remarkable progress, enabling high-quality ${\sim}4$-step sampling for large-scale text-conditional image and video diffusion models (DMs). However, further reducing the number of sampling steps becomes more and more challenging, suggesting that e…

Cited by 0 Source ↗code ↗Scholar ↗