Evgeny Burnaev
YOU?
Author Swipe
View article: Stability of the DuFort–Frankel Scheme on Unstructured Grids
Stability of the DuFort–Frankel Scheme on Unstructured Grids Open
The DuFort–Frankel scheme was introduced in the 1950s to solve parabolic equations, and has been widely used ever since due to its stability and explicit nature. However, for over seven decades, its application has been limited to Cartesia…
View article: How to model Human Actions distribution with Event Sequence Data
How to model Human Actions distribution with Event Sequence Data Open
This paper studies forecasting of the future distribution of events in human action sequences, a task essential in domains like retail, finance, healthcare, and recommendation systems where the precise temporal order is often less critical…
View article: Data-driven uncertainty-aware forecasting of sea ice conditions in the gulf of Ob based on satellite radar imagery
Data-driven uncertainty-aware forecasting of sea ice conditions in the gulf of Ob based on satellite radar imagery Open
View article: From Internal Representations to Text Quality: A Geometric Approach to LLM Evaluation
From Internal Representations to Text Quality: A Geometric Approach to LLM Evaluation Open
This paper bridges internal and external analysis approaches to large language models (LLMs) by demonstrating that geometric properties of internal model representations serve as reliable proxies for evaluating generated text quality. We v…
View article: EBES: Easy Benchmarking for Event Sequences
EBES: Easy Benchmarking for Event Sequences Open
View article: Self-Supervised Coarsening of Unstructured Grid with Automatic Differentiation
Self-Supervised Coarsening of Unstructured Grid with Automatic Differentiation Open
Due to the high computational load of modern numerical simulation, there is a demand for approaches that would reduce the size of discrete problems while keeping the accuracy reasonable. In this work, we present an original algorithm to co…
View article: Machine-learning models for predicting CO2 solubility in various brine systems: implications for carbon geo-storage
Machine-learning models for predicting CO2 solubility in various brine systems: implications for carbon geo-storage Open
View article: PersonalAI: A Systematic Comparison of Knowledge Graph Storage and Retrieval Approaches for Personalized LLM agents
PersonalAI: A Systematic Comparison of Knowledge Graph Storage and Retrieval Approaches for Personalized LLM agents Open
Personalizing language models by effectively incorporating user interaction history remains a central challenge in the development of adaptive AI systems. While large language models (LLMs) combined with Retrieval-Augmented Generation (RAG…
View article: Learning of Population Dynamics: Inverse Optimization Meets JKO Scheme
Learning of Population Dynamics: Inverse Optimization Meets JKO Scheme Open
Learning population dynamics involves recovering the underlying process that governs particle evolution, given evolutionary snapshots of samples at discrete time points. Recent methods frame this as an energy minimization problem in probab…
View article: Modeling and Analysis of Nonlinear Chaotic Mechanical Dynamics in Laser Scanning Systems
Modeling and Analysis of Nonlinear Chaotic Mechanical Dynamics in Laser Scanning Systems Open
This paper presents a novel approach to modeling and analyzing chaotic mechanical vibrations in laser scanning systems. The model explicitly incorporates nonlinear friction using the LuGre friction model. Experimental validation demonstrat…
View article: Exploration of geo-spatial data and machine learning algorithms for robust wildfire occurrence prediction
Exploration of geo-spatial data and machine learning algorithms for robust wildfire occurrence prediction Open
Wildfires play a pivotal role in environmental processes and the sustainable development of ecosystems. Timely responses can significantly reduce the damages and consequences caused by their spread. Several critical issues in wildfire beha…
View article: Feature-Level Insights into Artificial Text Detection with Sparse Autoencoders
Feature-Level Insights into Artificial Text Detection with Sparse Autoencoders Open
Artificial Text Detection (ATD) is becoming increasingly important with the rise of advanced Large Language Models (LLMs). Despite numerous efforts, no single algorithm performs consistently well across different types of unseen text or gu…
View article: Investigating the Impact of Quantization Methods on the Safety and Reliability of Large Language Models
Investigating the Impact of Quantization Methods on the Safety and Reliability of Large Language Models Open
Large Language Models (LLMs) are powerful tools for modern applications, but their computational demands limit accessibility. Quantization offers efficiency gains, yet its impact on safety and trustworthiness remains poorly understood. To …
View article: A Statistical Learning Perspective on Semi-dual Adversarial Neural Optimal Transport Solvers
A Statistical Learning Perspective on Semi-dual Adversarial Neural Optimal Transport Solvers Open
Neural network-based optimal transport (OT) is a recent and fruitful direction in the generative modeling community. It finds its applications in various fields such as domain translation, image super-resolution, computational biology and …
View article: Inverse Bridge Matching Distillation
Inverse Bridge Matching Distillation Open
Learning diffusion bridge models is easy; making them fast and practical is an art. Diffusion bridge models (DBMs) are a promising extension of diffusion models for applications in image-to-image translation. However, like many modern diff…
View article: InfoBridge: Mutual Information estimation via Bridge Matching
InfoBridge: Mutual Information estimation via Bridge Matching Open
Diffusion bridge models have recently become a powerful tool in the field of generative modeling. In this work, we leverage their power to address another important problem in machine learning and information theory, the estimation of the …
View article: On the practical applicability of modern DFT functionals for chemical computations. Case study of DM21 applicability for geometry optimization
On the practical applicability of modern DFT functionals for chemical computations. Case study of DM21 applicability for geometry optimization Open
Density functional theory (DFT) is probably the most promising approach for quantum chemistry calculations considering its good balance between calculations precision and speed. In recent years, several neural network-based functionals hav…
View article: Quantifying Logical Consistency in Transformers via Query-Key Alignment
Quantifying Logical Consistency in Transformers via Query-Key Alignment Open
View article: Self-Supervised Learning for Temporal Action Segmentation in Industrial and Manufacturing Videos
Self-Supervised Learning for Temporal Action Segmentation in Industrial and Manufacturing Videos Open
Reliable methods for process control are required in maintenance to prevent emergencies, maintain high quality of work, and minimize potential risks to workers. Strict adherence to technological processes is also an essential requirement f…
View article: GIFT-SW: Gaussian noise Injected Fine-Tuning of Salient Weights for LLMs
GIFT-SW: Gaussian noise Injected Fine-Tuning of Salient Weights for LLMs Open
View article: NeuSD: Surface Completion With Multi-View Text-to-Image Diffusion
NeuSD: Surface Completion With Multi-View Text-to-Image Diffusion Open
We present a new method for 3D surface reconstruction from multiple images where only a part of the object of interest is captured. Our approach builds on two recent developments: surface reconstruction with neural radiance fields for reco…
View article: A Physics-Informed Machine Learning Framework for Permafrost Stability Assessment
A Physics-Informed Machine Learning Framework for Permafrost Stability Assessment Open
Global warming accelerates permafrost degradation, compromising the reliability of critical infrastructure relied upon by over five million people daily. Additionally, permafrost thaw releases substantial methane emissions due to the thawi…
View article: Deep Spectral-Spatial Transformer for Robust Hyperspectral Image Segmentation in Varying Field Conditions
Deep Spectral-Spatial Transformer for Robust Hyperspectral Image Segmentation in Varying Field Conditions Open
Hyperspectral imaging serves as a powerful tool for environmental studies, enabling the capture of significant properties in the objects being analyzed. These hidden properties may not be discernible through traditional RGB analysis, thus …
View article: Topological Alternatives for Precision and Recall in Generative Models
Topological Alternatives for Precision and Recall in Generative Models Open
We introduce the Normalized Topological Divergence (NTD), a fully differentiable metric that simultaneously quantifies fidelity and diversity of generative models directly in raw pixel or spectrogram space, eliminating reliance on pretrain…
View article: Feature-Level Insights into Artificial Text Detection with Sparse Autoencoders
Feature-Level Insights into Artificial Text Detection with Sparse Autoencoders Open
View article: Challenges in data-driven geospatial modeling for environmental research and practice
Challenges in data-driven geospatial modeling for environmental research and practice Open
Machine learning-based geospatial applications offer unique opportunities for environmental monitoring due to domains and scales adaptability and computational efficiency. However, the specificity of environmental data introduces biases in…
View article: Deforming Implicit Neural Representation Generative Adversarial Network for Unsupervised Appearence Editing
Deforming Implicit Neural Representation Generative Adversarial Network for Unsupervised Appearence Editing Open
In this work, we present a new deep generative model for disentangling image shape from its appearance through differentiable warping. We propose to use implicit neural representations for modeling the deformation field and show that coord…
View article: Rethinking Graph Classification Problem in Presence of Isomorphism
Rethinking Graph Classification Problem in Presence of Isomorphism Open
There is an increasing interest in developing new models for graph classification problem that serves as a common benchmark for evaluation and comparison of GNNs and graph kernels. To ensure a fair comparison of the models several commonly…
View article: T-3DGS: Removing Transient Objects for 3D Scene Reconstruction
T-3DGS: Removing Transient Objects for 3D Scene Reconstruction Open
Transient objects in video sequences can significantly degrade the quality of 3D scene reconstructions. To address this challenge, we propose T-3DGS, a novel framework that robustly filters out transient distractors during 3D reconstructio…
View article: Rethinking Optimal Transport in Offline Reinforcement Learning
Rethinking Optimal Transport in Offline Reinforcement Learning Open
We propose a novel algorithm for offline reinforcement learning using optimal transport. Typically, in offline reinforcement learning, the data is provided by various experts and some of them can be sub-optimal. To extract an efficient pol…