Бобков Денис Николаевич
Факультет компьютерных наук
Должности
- Стажер-исследователь — Факультет компьютерных наук, Институт искусственного интеллекта и цифровых наук, Центр глубинного обучения и байесовских методов
Био
- · Начал работать в НИУ ВШЭ в 2026 году.
- · Научно-педагогический стаж: 3 года.
Образование
- 2023 · Бакалавриат: Национальный исследовательский университет "Высшая школа экономики", специальность «Прикладная математика и информатика», квалификация «Бакалавр»
Опыт работы
- · 2024: АИРИ: настоящее время Яндекс:
Публикации (2)
LoRA meets Riemannion: Muon Optimizer for Parametrization-independent Low-Rank Adapters
2026 · CHAPTER · en
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 manifold. This formulation eliminates the parametrization ambiguity present in standard Euclidean optimizers. Our framework integrates three key components to achieve this: (1) we derive Riemannion, a new Riemannian optimizer on the fixed-rank matrix manifold that generalizes the recently proposed Muon optimizer; (2) we develop a Riemannian gradient-informed LoRA initialization, and (3) we provide an efficient implementation without prominent overhead that uses automatic differentiation to compute arising geometric operations while adhering to best practices in numerical linear algebra. Comprehensive experimental results on both LLM and diffusion model architectures demonstrate that our approach yields consistent and noticeable improvements in convergence speed and final task performance over both standard LoRA and its state-of-the-art modifications.
The Devil is in the Details: StyleFeatureEditor for Detail-Rich StyleGAN Inversion and High Quality Image Editing
2024 · CHAPTER · en
The task of manipulating real image attributes through StyleGAN inversion has been extensively researched. This process involves searching latent variables from a well-trained StyleGAN generator that can synthesize a real image modifying these latent variables and then synthesizing an image with the desired edits. A balance must be struck between the quality of the reconstruction and the ability to edit. Earlier studies utilized the low-dimensional W-space for latent search which facilitated effective editing but struggled with reconstructing intricate details. More recent research has turned to the high-dimensional feature space F which successfully inverses the input image but loses much of the detail during editing. In this paper we introduce StyleFeatureEditor -- a novel method that enables editing in both w-latents and F-latents. This technique not only allows for the reconstruction of finer image details but also ensures their preservation during editing. We also present a new training pipeline specifically designed to train our model to accurately edit F-latents. Our method is compared with state-of-the-art encoding approaches demonstrating that our model excels in terms of reconstruction quality and is capable of editing even challenging out-of-domain examples.
Курсы (0)
Нет курсов.