Evgeny Burnaev

Principal Researcher@Applied AI Institute·俄罗斯·OpenReview

研究方向

stochastic processes · change-point detection · optimal stopping problems · anomaly detection · kernel methods · gaussian process models · bayesian optimization · surrogate modeling · 3D deep neural networks · point cloud segmentation · lidar data · voxel data · fMRI data · 3D shape retrieval · 3D shape classification · generative modeling · manifold learning · optimal transport · topological data analysis

Evgeny Burnaev

Universal Inverse Distillation for Matching Models with Real-Data Supervision (No GANs)

Q-RAG: Long Context Multi‑Step Retrieval via Value‑Based Embedder Training

InfoBridge: Mutual Information estimation via Bridge Matching

A Statistical Learning Perspective on Semi-dual Adversarial Neural Optimal Transport Solvers

T-3DGS: Removing Transient Objects for 3D Scene Reconstruction

HOW TO MODEL HUMAN ACTIONS DISTRIBUTION WITH EVENT SEQUENCE DATA

Learning of Population Dynamics: Inverse Optimization Meets JKO Scheme

Inverse Entropic Optimal Transport Solves Semi-supervised Learning via Data Likelihood Maximization

Uncovering Challenges of Solving the Continuous Gromov-Wasserstein Problem

One-Step Residual Shifting Diffusion for Image Super-Resolution via Distillation

Diffusion & Adversarial Schrödinger Bridges via Iterative Proportional Markovian Fitting

G-CUT3R: Guided 3D Reconstruction with Camera and Depth Prior Integration

From Internal Representations to Text Quality: A Geometric Approach to LLM Evaluation

Topology of Attention Detects Hallucinations in Code LLMs

Edge-wise topological divergence gaps: guiding search in combinatorial optimization

Listening to the Wise Few: Query–Key Alignment Unlocks Latent Correct Answers in Large Language Models

Multi-field sea ice data assimilation with a variational autoencoder

Learning meaningful geological fields representations by self-supervised methods

Inverse Bridge Matching Distillation

Uncovering Challenges of Solving the Continuous Gromov-Wasserstein Problem

A3D: Does Diffusion Dream about 3D Alignment?

Diffusion & Adversarial Schrödinger Bridges via Iterative Proportional Markovian Fitting

Listening to the Wise Few: Select-and-Copy Attention Heads for Multiple-Choice QA

Inverse Entropic Optimal Transport Solves Semi-supervised Learning via Data Likelihood Maximization

Exploring Source View Capability: Improve Generalizable 3D Reconstruction with Multi-view Context from Source Views

Exploiting Topology of Protein Language Model Attention Maps for Token Classification

Learnable Stability-Aware Unstructured Grid Coarsening Using Graph Neural Networks for Accelerated Physics Simulations

Data-Driven Uncertainty-Aware Forecasting of Sea Ice Conditions in the Gulf of Ob Based on Satellite Radar Imagery

EBES: Easy Benchmarking for Event Sequences

Atmospheric Radiation Parameterization by Neural Ordinary Differential Equations and Related Models

Differentiable Implicit Solver on Graph Neural Networks for Forward and Inverse Problems

GIFT-SW: Gaussian noise Injected Fine-Tuning of Salient Weights for LLMs