4 citations · 28 across the 86 of their papers we have counts for
41 papers · 1 filter
Ky Fan Norms and Beyond: Dual Norms and Combinations for Matrix Optimization
Alexey Kravatskiy, Ivan Kozyrev, Nikolai Kozlov +3
In this article, we explore the use of various matrix norms for optimizing functions of weight matrices, a crucial problem in deep learning. Moving beyond the spectral norm that un…
GigaEvo: An Open Source Optimization Framework Powered By LLMs And Evolution Algorithms
Valentin Khrulkov, Andrey Galichin, Denis Bashkirov +5
Recent advances in LLM-guided evolutionary computation, particularly AlphaEvolve (Novikov et al., 2025; Georgiev et al., 2025), have demonstrated remarkable success in discovering…
Multi-Agent GraphRAG: A Text-to-Cypher Framework for Labeled Property Graphs
Anton Gusarov, Anastasia Volkova, Valentin Khrulkov +3
While Retrieval-Augmented Generation (RAG) methods commonly draw information from unstructured documents, the emerging paradigm of GraphRAG aims to leverage structured data such as…
FMMI: Flow Matching Mutual Information Estimation
Ivan Butakov, Alexander Semenenko, Valeriya Kirova +2
We introduce a novel Mutual Information (MI) estimator that fundamentally reframes the discriminative approach. Instead of training a classifier to discriminate between joint and m…
T-MLA: A targeted multiscale log-exponential attack framework for neural image compression
Nikolay I. Kalmykov, Razan Dibo, Kaiyu Shen +4
Neural image compression (NIC) has become the state-of-the-art for rate-distortion performance, yet its security vulnerabilities remain significantly less understood than those of…
CLARITY: Clinical Assistant for Routing, Inference, and Triage
Vladimir Shaposhnikov, Aleksandr Nesterov, Ilia Kopanichuk +7
We present CLARITY (Clinical Assistant for Routing, Inference and Triage), an AI-driven platform designed to facilitate patient-to-specialist routing, clinical consultations, and s…
Matcha: Multi-Stage Riemannian Flow Matching for Accurate and Physically Valid Molecular Docking
Daria Frolova, Talgat Daulbaev, Egor Sevriugov +4
Accurate prediction of protein-ligand binding poses is crucial for structure-based drug design, yet existing methods struggle to balance speed, accuracy, and physical plausibility.…
OrtSAE: Orthogonal Sparse Autoencoders Uncover Atomic Features
Anton Korznikov, Andrey Galichin, Alexey Dontsov +3
Sparse autoencoders (SAEs) are a technique for sparse decomposition of neural network activations into human-interpretable features. However, current SAEs suffer from feature absor…
How to Evaluate Medical AI
Ilia Kopanichuk, Petr Anokhin, Vladimir Shaposhnikov +5
The integration of artificial intelligence (AI) into medical diagnostic workflows requires robust and consistent evaluation methods to ensure reliability, clinical relevance, and t…
Spectral Analysis of the Weighted Frobenius Objective
Vladislav Trifonov, Ivan Oseledets, Ekaterina Muravleva
We analyze a weighted Frobenius loss for approximating symmetric positive definite matrices in the context of preconditioning iterative solvers. Unlike the standard Frobenius norm,…
Random Direct Preference Optimization for Radiography Report Generation
Valentin Samokhin, Boris Shirokikh, Mikhail Goncharov +5
Radiography Report Generation (RRG) has gained significant attention in medical image analysis as a promising tool for alleviating the growing workload of radiologists. However, de…
Deep Learning for Subspace Regression
Vladimir Fanaskov, Vladislav Trifonov, Alexander Rudikov +2
It is often possible to perform reduced order modelling by specifying linear subspace which accurately captures the dynamics of the system. This approach becomes especially appeali…
The Rogue Scalpel: Activation Steering Compromises LLM Safety
Anton Korznikov, Andrey Galichin, Alexey Dontsov +3
Activation steering is a promising technique for controlling LLM behavior by adding semantically meaningful vectors directly into a model's hidden states during inference. It is of…
Low-rank surrogate modeling and stochastic zero-order optimization for training of neural networks with black-box layers
Andrei Chertkov, Artem Basharin, Mikhail Saygin +3
The growing demand for energy-efficient, high-performance AI systems has led to increased attention on alternative computing platforms (e.g., photonic, neuromorphic) due to their p…
Cluster Topology-Driven Placement of Experts Reduces Network Traffic in MoE Inference
Danil Sivtsov, Aleksandr Katrutsa, Ivan Oseledets
Efficient deployment of a pre-trained LLM to a cluster with multiple servers is a critical step for providing fast responses to users' queries. The recent success of Mixture-of-Exp…
Speech-to-LaTeX: New Models and Datasets for Converting Spoken Equations and Sentences
Dmitrii Korzh, Dmitrii Tarasov, Artyom Iudin +6
Conversion of spoken mathematical expressions is a challenging task that involves transcribing speech into a strictly structured symbolic representation while addressing the ambigu…
Quasi-Random Physics-informed Neural Networks
Tianchi Yu, Ivan Oseledets
Physics-informed neural networks have shown promise in solving partial differential equations (PDEs) by integrating physical constraints into neural network training, but their per…
Geopolitical biases in LLMs: what are the "good" and the "bad" countries according to contemporary language models
Mikhail Salnikov, Dmitrii Korzh, Ivan Lazichny +7
This paper evaluates geopolitical biases in LLMs with respect to various countries though an analysis of their interpretation of historical events with conflicting national perspec…
Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models
Pengyi Li, Matvey Skripkin, Alexander Zubrey +2
Large language models (LLMs) excel at reasoning, yet post-training remains critical for aligning their behavior with task goals. Existing reinforcement learning (RL) methods often…
Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts
Danil Sivtsov, Ivan Rodkin, Gleb Kuzmin +2
Transformer models struggle with long-context inference due to their quadratic time and linear memory complexity. Recurrent Memory Transformers (RMTs) offer a solution by reducing…
Listener-Rewarded Thinking in VLMs for Image Preferences
Alexander Gambashidze, Li Pengyi, Matvey Skripkin +5
Training robust and generalizable reward models for human visual preferences is essential for aligning text-to-image and text-to-video generative models with human intent. However,…
Geological Field Restoration through the Lens of Image Inpainting
Vladislav Trifonov, Ivan Oseledets, Ekaterina Muravleva
We study an ill-posed problem of geological field reconstruction under limited observations. Engineers often have to deal with the problem of reconstructing the subsurface geologic…
Curse of Slicing: Why Sliced Mutual Information is a Deceptive Measure of Statistical Dependence
Alexander Semenenko, Ivan Butakov, Alexey Frolov +1
Sliced Mutual Information (SMI) is widely used as a scalable alternative to mutual information for measuring non-linear statistical dependence. Despite its advantages, such as fast…
One Task Vector is not Enough: A Large-Scale Study for In-Context Learning
Pavel Tikhonov, Ivan Oseledets, Elena Tutubalina
In-context learning (ICL) enables Large Language Models (LLMs) to adapt to new tasks using few examples, with task vectors - specific hidden state activations - hypothesized to enc…