43 citations · 71 across the 29 of their papers we have counts for
30 papers
Policy-Mask: Budget-Aware Adaptation of Diffusion Features to Discriminative Tasks
Ivan Listopadov, Maksim Nakhodnov, Aibek Alanov
Selecting intermediate features from a frozen diffusion model for discriminative tasks is non-trivial because the useful signal is distributed across the denoising trajectory, netw…
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…
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…
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…
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…
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…
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…
GAS: Improving Discretization of Diffusion ODEs via Generalized Adversarial Solver
Aleksandr Oganov, Ilya Bykov, Eva Neudachina +7
While diffusion models achieve state-of-the-art generation quality, they still suffer from computationally expensive sampling. Recent works address this issue with gradient-based o…
Guided Star-Shaped Masked Diffusion
Viacheslav Meshchaninov, Egor Shibaev, Artem Makoian +5
The performance of pre-trained masked diffusion models is often constrained by their sampling procedure, which makes decisions irreversible and struggles in low-step generation reg…
Heeding the Inner Voice: Aligning ControlNet Training via Intermediate Features Feedback
Nina Konovalova, Maxim Nikolaev, Andrey Kuznetsov +1
Despite significant progress in text-to-image diffusion models, achieving precise spatial control over generated outputs remains challenging. ControlNet addresses this by introduci…
LoRA meets Riemannion: Muon Optimizer for Parametrization-independent Low-Rank Adapters
Vladimir Bogachev, Vladimir Aletov, Alexander Molozhavenko +4
This work presents a novel, fully Riemannian framework for Low-Rank Adaptation (LoRA) that geometrically treats low-rank adapters by optimizing them directly on the fixed-rank mani…
T-LoRA: Single Image Diffusion Model Customization Without Overfitting
Vera Soboleva, Aibek Alanov, Andrey Kuznetsov +1
While diffusion model fine-tuning offers a powerful approach for customizing pre-trained models to generate specific objects, it frequently suffers from overfitting when training s…
Inverse-and-Edit: Effective and Fast Image Editing by Cycle Consistency Models
Ilia Beletskii, Andrey Kuznetsov, Aibek Alanov
Recent advances in image editing with diffusion models have achieved impressive results, offering fine-grained control over the generation process. However, these methods are compu…
ImageReFL: Balancing Quality and Diversity in Human-Aligned Diffusion Models
Dmitrii Sorokin, Maksim Nakhodnov, Andrey Kuznetsov +1
Recent advances in diffusion models have led to impressive image generation capabilities, but aligning these models with human preferences remains challenging. Reward-based fine-tu…
FastFace: Tuning Identity Preservation in Distilled Diffusion via Guidance and Attention
Sergey Karpukhin, Vadim Titov, Andrey Kuznetsov +1
In latest years plethora of identity-preserving adapters for a personalized generation with diffusion models have been released. Their main disadvantage is that they are dominantly…
DreamBoothDPO: Improving Personalized Generation using Direct Preference Optimization
Shamil Ayupov, Maksim Nakhodnov, Anastasia Yaschenko +2
Personalized diffusion models have shown remarkable success in Text-to-Image (T2I) generation by enabling the injection of user-defined concepts into diverse contexts. However, bal…
Beyond Fine-Tuning: A Systematic Study of Sampling Techniques in Personalized Image Generation
Vera Soboleva, Maksim Nakhodnov, Aibek Alanov
Personalized text-to-image generation aims to create images tailored to user-defined concepts and textual descriptions. Balancing the fidelity of the learned concept with its abili…
MaterialFusion: High-Quality, Zero-Shot, and Controllable Material Transfer with Diffusion Models
Kamil Garifullin, Maxim Nikolaev, Andrey Kuznetsov +1
Manipulating the material appearance of objects in images is critical for applications like augmented reality, virtual prototyping, and digital content creation. We present Materia…
CLEAR: Character Unlearning in Textual and Visual Modalities
Alexey Dontsov, Dmitrii Korzh, Alexey Zhavoronkin +6
Machine Unlearning (MU) is critical for removing private or hazardous information from deep learning models. While MU has advanced significantly in unimodal (text or vision) settin…
Guide-and-Rescale: Self-Guidance Mechanism for Effective Tuning-Free Real Image Editing
Vadim Titov, Madina Khalmatova, Alexandra Ivanova +2
Despite recent advances in large-scale text-to-image generative models, manipulating real images with these models remains a challenging problem. The main limitations of existing e…
Group and Shuffle: Efficient Structured Orthogonal Parametrization
Mikhail Gorbunov, Nikolay Yudin, Vera Soboleva +3
The increasing size of neural networks has led to a growing demand for methods of efficient fine-tuning. Recently, an orthogonal fine-tuning paradigm was introduced that uses ortho…
HairFastGAN: Realistic and Robust Hair Transfer with a Fast Encoder-Based Approach
Maxim Nikolaev, Mikhail Kuznetsov, Dmitry Vetrov +1
Our paper addresses the complex task of transferring a hairstyle from a reference image to an input photo for virtual hair try-on. This task is challenging due to the need to adapt…
Star-Shaped Denoising Diffusion Probabilistic Models
Andrey Okhotin, Dmitry Molchanov, Vladimir Arkhipkin +4
Denoising Diffusion Probabilistic Models (DDPMs) provide the foundation for the recent breakthroughs in generative modeling. Their Markovian structure makes it difficult to define…
StyleDomain: Efficient and Lightweight Parameterizations of StyleGAN for One-shot and Few-shot Domain Adaptation
Aibek Alanov, Vadim Titov, Maksim Nakhodnov +1
Domain adaptation of GANs is a problem of fine-tuning GAN models pretrained on a large dataset (e.g. StyleGAN) to a specific domain with few samples (e.g. painting faces, sketches,…