Source author record

Leonid Bedratyuk

Explore this author’s publications, collaborators and research topics. This catalog record has not been claimed by its author.

ResearcherUnclaimed source record

Catalog footprint

Research overview

23works
10topics
1close collaborators

Published work

23 publications

preprint2026arXiv

Controlled Paraphrase Geometry in Sentence Embedding Space: Local Manifold Modeling and Latent Probing

The paper studies the local geometry of embedding clouds induced by \emph{controlled local classes of semantically close sentences}. The central question is how controlled paraphrase-like semantic variation is organized in sentence embedding space and whether this local structure can be explicitly modeled by low-degree fitted carriers. We introduce a local geometric modeling scheme based on affine, quadratic, and cubic fitted models. We also use a surface-based latent probing procedure that constructs synthetic latent points in a reduced local PCA space with respect to the fitted carrier. The procedure is intended as an offline method for representation-space analysis, local manifold modeling, and geometry-aware latent probing. Generated latent points are evaluated using criteria that measure consistency with the fitted surface, preservation of neighborhood structure, agreement with the empirical distribution, stability of Hessian-based second-order shape descriptors, and stability of fitted-model coefficients. Experiments on controlled sets of semantically close sentences show that nonlinear local models describe embedding clouds more accurately than affine models. Surface-based generation provides strong fitted-geometry fidelity, including surface consistency, Hessian-based shape consistency, and coefficient consistency. Downstream experiments show that geometric validity of synthetic latent points does not automatically translate into improved classification performance. The results support explicit local geometric modeling of sentence embedding space and highlight the need to distinguish geometric validity from discriminative utility. As a resource contribution, we introduce \textbf{CoPaGE-300K}, a controlled template-based dataset of semantically close sentence variants with slot-level annotations and precomputed sentence embeddings.

preprint2026arXiv

MSIQ: Moment-based Scale-Invariant Quality Measure for Single Image Super-Resolution

Assessing the quality of single image super-resolution (SISR) results remains an open methodological problem. Common full-reference metrics (PSNR, SSIM, LPIPS) do not explicitly evaluate the preservation of the geometric structure of images, which is critical for the correctness of scale-based reconstruction. In addition, they require the forced alignment of images to the same size (\textit{forced resizing}), which introduces an external interpolation error into the evaluation process. This paper proposes a diagnostic scale-invariant quality measure, MSIQ (\textit{Moment-based Scale-Invariant Quality}), based on the comparison of normalized central geometric moments of two images. MSIQ enables direct comparison of images with different spatial resolutions without resizing, is mathematically deterministic (\textit{model-free}), and has an analytical form. To provide a theoretical basis for the approach, we introduce a conceptual distinction between the ability of metrics to monotonically track degradation (\textit{tracking ability}) and their geometric selectivity (\textit{geometric specificity}). The experimental validation confirmed the stability of MSIQ under uniform scaling and, at the same time, revealed the high sensitivity of traditional metrics to the choice of interpolation method. The results show that MSIQ has pronounced geometric selectivity: the proposed measure effectively separates geometric deformations from non-geometric artifacts, in particular JPEG compression, unlike pixel-based and perceptual metrics. It is also shown that the response of MSIQ to structural perturbations remains stable across different classes of SR algorithms, including DNN models with different architectures. The proposed measure is a complementary diagnostic tool for domains where geometric fidelity has priority, in particular medical imaging and remote sensing.

preprint2026arXiv

Relative Invariants from Moving Frames on an Extended Manifold

A constructive modification of the moving frame method is developed in this paper for the construction of relative invariants of regular Lie group actions. Let a relative invariant II of weight ωω transform according to the rule I(g⋅x)=μ(g,x)ωI(x), I(g \cdot \boldsymbol x) = μ(g, \boldsymbol x)^ω I(\boldsymbol x), where μ:G×M→R×μ: G \times \mathcal{M} \to \mathbb{R}^\times is a scalar multiplier (1-cocycle). It is shown that the cocycle property of μμ is equivalent to the well-definedness of the twisted group action on the extended manifold M^=M×R×\widehat{\mathcal{M}} = \mathcal{M} \times \mathbb{R}^\times, and that relative invariants on M\mathcal{M} are in one-to-one correspondence with absolute invariants of this action on M^\widehat{\mathcal{M}}. The main result is that, given a moving frame, the invariantization of the multiplier is a canonical relative invariant of weight −1-1. This enables the constructive realization of any weight and yields an explicit formula for an arbitrary relative invariant in terms of the fundamental absolute invariants and the invariantized multiplier. Examples are provided to demonstrate the application of the proposed approach for the projective group PGL(3,R)PGL(3, \mathbb{R}).

preprint2011arXiv

Multivariate Poincaré series for algebras of SL2SL_2-invariants

Let $\mathcal{C}_{\mathbi{d}},$ $\mathcal{I}_{\mathbi{d}},$ $\mathbi{d}{=}(d_1,d_2,..., d_n)$ be the algebras of join covariants and joint invariants of the nn binary forms of degrees d1,d2,...,dn.d_1,d_2,..., d_n. Formulas for computation of the multivariate Poincaré series $\mathcal{P}(\mathcal{C}_{\mathbi{d}},z_1,z_2,...,z_n,t)$ and $\mathcal{P}(\mathcal{I}_{\mathbi{d}},z_1,z_2,...,z_n)$ are found.

preprint2009arXiv

The Poincaré series of the joint invariants and covariants of the two binary forms

Let Id1,d2\mathcal{I}_{d_1,d_2} and Cd1,d2\mathcal{C}_{d_1,d_2} be the algebras of joint invariants and joint covariants of the two binary forms of degrees d1d_1 and d2.d_2. Formulas for computation of the Poincaré series PId1,d2(z),\mathcal{PI}_{d_1,d_2}(z), PCd1,d2(z) \mathcal{PC}_{d_1,d_2}(z) of the algebras is found. By using these formulas, we have computed the series for d1,d2≤20.d_1,d_2 \leq 20.

Research graph

See the researcher in context

Open full explorer

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.