Sessions
-
Session 1: Applied ML
HSE University Cultural Centre, Z201
October 28, 10:00
TransPath: Learning Heuristics for Grid-Based Pathfinding via Transformers
Anton Andreychuk, Alexander Panov, Konstantin Yakovlev
Evaluating Robustness and Uncertainty of Graph Models Under Structural Distributional Shifts
Gleb Bazhenov
Characterizing Graph Datasets for Node Classification: Homophily-Heterophily Dichotomy and Beyond
Oleg Platonov
Mars: Masked automatic ranks selection in tensor decompositions
Maxim Kodryan, Dmitry Vetrov, Dmitry Kropotov
Constructive TT-representation of the tensors given as index interaction functions with applications
Gleb Ryzhakov, Ivan Oseledets
-
Session 2: Theoretical ML 1
Anti-Exploration by Random Network Distillation
Alexander Nikulin
Fast Rates for Maximum Entropy Exploration
Alexey Naumov, Daniil Tiapkin
Algorithm for Constrained Markov Decision Process with Linear Convergence
Varvara Rudenko, Alexander Gasnikov
Towards true discovery of the differential equations
Alexander Hvatov
General Covariance Data Augmentation for Neural PDE Solvers
Tianchi Yu
-
Session 3: NLP
The Impact of Cross-Lingual Adjustment of Contextual Word Representations on Zero-Shot Transfer
Pavel Efimov
Efficient Out-of-Domain Detection for Sequence to Sequence Models
Sergey Petrakov, Alexander Panchenko
A System for Answering Simple Questions in Multiple Languages
Mikhail Salnikov
Hybrid Uncertainty Estimation for Selective Text Classification in Ambiguous Tasks
Artem Vazhentsev
SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression
Denis Kuznedelev
Layerwise universal adversarial attack on NLP models
Olga Tsymboi, Ivan Oseledets
-
Session 4: Theoretical ML 2
Structure of Universal Formulas
Dmitry Yarotsky
Is Consensus Acceleration Possible in Decentralized Optimization over Slowly Time-Varying Networks?
Alexander Rogozin, Alexander Gasnikov
First Order Methods with Markovian Noise: from Acceleration to Variational Inequalities
Sergey Samsonov, Alexander Gasnikov, Alexey Naumov, Marina Shehukova
Gradient Boosting Performs Gaussian Process Inference
Artem Beliakov
Accelerated Zeroth-order Method for Non-Smooth Stochastic Convex Optimization Problem with Infinite Variance
Darina Dvinskikh, Alexander Lobanov, Nikita Kornilov
Exploring Local Norms in Exp-concave Statistical Learning
Nikita Puchkin
-
Session 5: Generative modeling and representation learning 1
Tabddpm: Modelling tabular data with diffusion models
Ivan Rubachev
NEURAL OPTIMAL TRANSPORT
Daniil Selikhanovich, Evgeny Burnaev, Alexander Korotin
KERNEL NEURAL OPTIMAL TRANSPORT
Alexander Korotin, Daniil Selikhanovich, Evgeny Burnaev
Learning topology-preserving data representations
Ilya Trofimov, Daniil Cherniavskii, Eduard Tulchinskii, Nikita Balabin, Evgeny Burnaev, Serguei Barannikov
SYMBOLIC DISENTANGLED REPRESENTATIONS IN HY- PERDIMENSIONAL LATENT SPACE
Alexandr Korchemnyi, Alexey Kovalev, Alexander Panov
To Stay or Not to Stay in the Pre-train Basin: Insights on Ensembling in Transfer Learning
Ildus Sadrtdinov
-
Session 6: CV 1
Integral Neural Networks
Kirill Solodskikh, Azim Kurbanov, Ruslan Aydarkhanov, Irina Zhelavskaya, Yuri Parfenov, Dehua Song, Stamatios Lefkimmiatis
Slovo: Russian Sign Language Dataset
Elizaveta Petrova, Karina Kvanchiani
FIANCEE: Faster Inference of Adversarial Networks via Conditional Early Exits
Polina Karpikova, Anastasia Yachenko, Ekaterina Radionova
Multi-sensor large-scale dataset for multi-view 3D reconstruction
Savva Ignatyev, Oleg Voynov, Ruslan Rakhimov
Deep Lucky Imaging for Astrophotography
Singh Suraj
NeSS-ST: Detecting Good and Stable Keypoints with a Neural Stability Score and the Shi-Tomasi detector
Ferrer Gonzalo, Konstantin Pakulev, Alexander Vakhitov
-
Session 7: Generative modeling and representation learning 2
Entropic Neural Optimal Transport via Diffusion Processes
Nikita Gushchin, Aleksandr Kolesov, Evgeny Burnaev, Petr Mokrov, Alexander Korotin
Building the Bridge of Schrodinger: A Continuous Entropic Optimal Transport Benchmark
Nikita Gushchin, Alexander Kolesov, Petr Mokrov, Evgeny Burnaev, Alexander Korotin
Extremal Domain Translation with Neural Optimal Transport
Milena Gazdieva, Daniil Selikhanovich, Evgeny Burnaev, Alexander Korotin
Understanding DDPM Latent Codes Through Optimal Transport
Valentin Khrulkov, Gleb Ryzhakov, Andrei Chertkov, Ivan Oseledets
Kandinsky: an Improved Text-to-Image Synthesis with Image Prior and Latent Diffusion
Vladimir Arkhipkin, Denis Dimitrov
-
Session 8: CV 2
Facial Expression Recognition with Adaptive Frame Rate based on Multiple Testing Correction
Andrey Savchenko
Fast Adversarial CNN-based Perturbation Attack on No-Reference Image- and Video-Quality Metrics
Ekaterina Shumitskaya, Anastasia Antsiferova, Dmitriy S. Vatolin
Physically-Plausible Illumination Distribution Estimation
Egor Ershov
StyleDomain: Efficient and Lightweight Parameterizations of StyleGAN for One-shot and Few-shot Domain Adaptation
Aibek Alanov, Vadim Titov, Maksim Nakhodnov, Dmitry Vetrov
Differentiable Rendering with Reparameterized Volume Sampling
Nikita Morozov, Kirill Struminsky