9 citations · 20 across the 12 of their papers we have counts for
17 papers
FlashAttention with Statistics: Low-Overhead Attention Features for Compact Hallucination Detectors
Andrei Volodichev, Maksim Savichev, Nikita Sviridov +3
Large language models can produce fluent answers that the supplied context does not support. A compact frozen proxy model can detect such answers by reading the context and another…
Recursive Offline Distillation via Entropy Gain Sampling and Answer Mixing
Andrey Goncharov, Daniil Vyazhev, Simon Epanov +1
Distillation of reasoning chains from Large Language Models (LLMs) into their smaller siblings is a standard training approach. Frequently, researchers do not have full access to a…
Reliable Risk Estimation with Kernel Mean Matching under Dependent Sampling
Alexey Zaytsev, Diana Koldasbayeva, Egor Serov
Kernel Mean Matching (KMM) estimates risk under covariate shift by reweighting labelled source samples so that their kernel mean embedding matches that of unlabeled target samples.…
MercerFlow: Flow Matching in a Kernel-Induced Latent Space for Probabilistic Forecasting
Ilya Kuleshov, Egor Serov, Alexey Zaytsev
Recent work has shown that probabilistic flow matching for time series forecasting benefits from a data-matched prior. The resulting prior introduces local correlations, which a se…
Mixed-Prior Decision Risk for Open-Set Recognition
L. A. Erlygin, P. D. Proskura, A. A. Zaytsev
In open-set recognition (OSR), a probe must either be identified as one of the known gallery classes or rejected as unknown, so three error types coexist: false acceptance, false r…
Portfolio Selection via Topological Data Analysis
Petr Sokerin, Kristian Kuznetsov, Elizaveta Makhneva +1
Portfolio management is an essential part of investment decision-making. However, traditional methods often fail to deliver reasonable performance. This problem stems from the inab…
Uncertainty Estimation of Transformers' Predictions via Topological Analysis of the Attention Matrices
Elizaveta Kostenok, Daniil Cherniavskii, Alexey Zaytsev
Transformer-based language models have set new benchmarks across a wide range of NLP tasks, yet reliably estimating the uncertainty of their predictions remains a significant chall…
Hiding Backdoors within Event Sequence Data via Poisoning Attacks
Alina Ermilova, Elizaveta Kovtun, Dmitry Berestnev +1
The financial industry relies on deep learning models for making important decisions. This adoption brings new danger, as deep black-box models are known to be vulnerable to advers…
Label Attention Network for Temporal Sets Prediction: You Were Looking at a Wrong Self-Attention
Elizaveta Kovtun, Galina Boeva, Andrey Shulga +1
Most user-related data can be represented as a sequence of events associated with a timestamp and a collection of categorical labels. For example, the purchased basket of goods and…
Robust representations of oil wells' intervals via sparse attention mechanism
Alina Ermilova, Nikita Baramiia, Valerii Kornilov +2
Transformer-based neural network architectures achieve state-of-the-art results in different domains, from natural language processing (NLP) to computer vision (CV). The key idea o…
Self-supervised similarity models based on well-logging data
Sergey Egorov, Narek Gevorgyan, Alexey Zaytsev
Adopting data-based approaches leads to model improvement in numerous Oil&Gas logging data processing problems. These improvements become even more sound due to new capabilities pr…
Non-contrastive representation learning for intervals from well logs
Alexander Marusov, Alexey Zaytsev
The representation learning problem in the oil & gas industry aims to construct a model that provides a representation based on logging data for a well interval. Previous attempts…
Predicting spatial distribution of Palmer Drought Severity Index
V. Grabar, A. Lukashevich, A. Zaytsev
The probability of a drought for a particular region is crucial when making decisions related to agriculture. Forecasting this probability is critical for management and challengin…
Usage of specific attention improves change point detection
Anna Dmitrienko, Evgenia Romanenkova, Alexey Zaytsev
The change point is a moment of an abrupt alteration in the data distribution. Current methods for change point detection are based on recurrent neural methods suitable for sequent…
Deep learning model solves change point detection for multiple change types
Alexander Stepikin, Evgenia Romanenkova, Alexey Zaytsev
A change points detection aims to catch an abrupt disorder in data distribution. Common approaches assume that there are only two fixed distributions for data: one before and anoth…
Similarity learning for wells based on logging data
Evgenia Romanenkova, Alina Rogulina, Anuar Shakirov +6
One of the first steps during the investigation of geological objects is the interwell correlation. It provides information on the structure of the objects under study, as it compr…
InDiD: Instant Disorder Detection via Representation Learning
Evgenia Romanenkova, Alexander Stepikin, Matvey Morozov +1
For sequential data, a change point is a moment of abrupt regime switch in data streams. Such changes appear in different scenarios, including simpler data from sensors and more ch…