Ключевые доклады

Gradient Flow Through Diagram Expansions: Learning Regimes and Explicit Solutions

ICML

Dmitry Yarotsky, Eugene Golikov, Yaroslav Gusev

Gaussian Approximation and Multiplier Bootstrap for Stochastic Gradient Descent

AISTATS

Marina Sheshukova, Sergey Samsonov, Denis Belomestny, Eric Moulines, Qi-Man Shao, Zhuo-Song Zhang. Alexey Naumov

FMMI: Flow Matching Mutual Information Estimation

NeurIPS

Ivan Butakov, Alexander Semenenko, Valeriia Kirova, Ivan Oseledets, Alexey Frolov

LoRA meets Riemannion: Muon Optimizer for Parametrization-independent Low-Rank Adapters

ICLR

Vladimir Bogachev, Vladimir Aletov, Alexander Molozhavenko, Denis Bobkov, Vera Soboleva, Aibek Alanov, Maxim Rakhuba

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

ICLR

Nikita Maksimovich Kornilov, David Li, Tikhon Mavrin, Aleksei Leonov, Nikita Gushchin, Evgeny Burnaev, Iaroslav Sergeevich Koshelev, Alexander Korotin

Object-Centric Latent Action Learning

AAAI

Albina Klepach, Alexander Nikulin, Ilya Zisman, Denis Tarasov, Alexander Derevyagin, Andrei Polubarov, Nikita Lyubaykin, Igor Kiselev, Vladislav Kurenkov

Detecting the Future: All-at-Once Event Sequence Forecasting with Horizon Matching

AAAI

Ivan Karpukhin, Andrey Savchenko

Lightweight Optimal-Transport Harmonization on Edge Devices

AAAI

Maria Larchenko, Dmitry Guskov, Alexander Lobashev, Georgy Derevyanko

Don't Blind Your VLA: Aligning Visual Representations for OOD Generalization

AAMAS

Nikita Kachaev, Mikhail Kolosov, Daniil Zelezetsky, Alexey K. Kovalev, Aleksandr I. Panov