collaborators

18 papers

cs.CV2026

Rethinking Pixel Mean Flows via Interval Denoiser

Alexander Zaytsev, Dmitry Baranchuk, Alexander Korotin +1

Modern diffusion and flow-based models are increasingly moving toward few-step, latent-free generation to bypass the computational overhead of multi-step sampling and the reconstru…

cs.CV2026

DifFRACT: Diffusion Feature Reconstruction and Attribution for Circuit Tracing

Artyom Mazur, Nina Konovalova, Aibek Alanov

Mechanistic interpretability seeks to explain neural network behavior by decomposing model computations into interpretable features and circuits. While transcoder-based circuit tra…

cs.CV2026

ReCache: Learning Budget-Aware Caching Schedules for Diffusion Models via REINFORCE

Mishan Aliev, Eva Neudachina, Ilya Bykov +4

Modern diffusion models generate high-quality images and videos, but their iterative denoising process makes inference expensive. Feature caching accelerates sampling by reusing or…

cs.CV2026

ATATA: One Algorithm to Align Them All

Boyi Pang, Savva Ignatyev, Vladimir Ippolitov +8

We suggest a new multi-modal algorithm for joint inference of paired structurally aligned samples with Rectified Flow models. While some existing methods propose a codependent gene…

cs.CV2026

SHIFT: Steering Hidden Intermediates in Flow Transformers

Nina Konovalova, Andrey Kuznetsov, Aibek Alanov

Diffusion models have become leading approaches for high-fidelity image generation. Recent DiT-based diffusion models, in particular, achieve strong prompt adherence while producin…

cs.CV2026

OrthoFuse: Training-free Riemannian Fusion of Orthogonal Style-Concept Adapters for Diffusion Models

Ali Aliev, Kamil Garifullin, Nikolay Yudin +5

In a rapidly growing field of model training there is a constant practical interest in parameter-efficient fine-tuning and various techniques that use a small amount of training da…