Наши работы
Omut AI наследует исследовательскую команду T-Bank Research, в которой мы занимаемся созданием новых алгоритмов в AI
2024
2023
2022
Viacheslav Sinii
Alexander Nikulin
Vladislav Kurenkov
Ilya Zisman
Sergey Kolesnikov
Alexander Nikulin
Vladislav Kurenkov
Ilya Zisman
Sergey Kolesnikov
In-Context Reinforcement Learning for Variable Action Spaces
ICML 2024
Подробнее
Stanislav Dereka
Ivan Karpukhin
Maksim Zhdanov
Sergey Kolesnikov
Ivan Karpukhin
Maksim Zhdanov
Sergey Kolesnikov
Diversifying Deep Ensembles: A Saliency Map Approach for Enhanced OOD Detection, Calibration, and Accuracy
IEEE ICIP 2024
Подробнее
Yaroslav Aksenov
Nikita Balagansky
Sofia Maria Lo Cicero Vaina
Boris Shaposhnikov
Alexey Gorbatovski
Daniil Gavrilov
Nikita Balagansky
Sofia Maria Lo Cicero Vaina
Boris Shaposhnikov
Alexey Gorbatovski
Daniil Gavrilov
Linear Transformers with Learnable Kernel Functions are Better In-Context Models
ACL 2024
Подробнее
Ilya Zisman
Vladislav Kurenkov
Alexander Nikulin
Viacheslav Sinii
Sergey Kolesnikov
Vladislav Kurenkov
Alexander Nikulin
Viacheslav Sinii
Sergey Kolesnikov
Emergence of In-Context Reinforcement Learning from Noise Distillation
ICML 2024
Подробнее
Alexey Gorbatovski
Boris Shaposhnikov
Alexey Malakhov
Nikita Surnachev
Yaroslav Aksenov
Ian Maksimov
Nikita Balagansky
Daniil Gavrilov
Boris Shaposhnikov
Alexey Malakhov
Nikita Surnachev
Yaroslav Aksenov
Ian Maksimov
Nikita Balagansky
Daniil Gavrilov
Learn Your Reference Model for Real Good Alignment
Preprint
Подробнее
Denis Tarasov
Vladislav Kurenkov
Alexander Nikulin
Sergey Kolesnikov
Vladislav Kurenkov
Alexander Nikulin
Sergey Kolesnikov
Revisiting the Minimalist Approach to Offline Reinforcement Learning
NeurIPS 2023
Подробнее
Denis Tarasov
Alexander Nikulin
Dmitry Akimov
Vladislav Kurenkov
Sergey Kolesnikov
Alexander Nikulin
Dmitry Akimov
Vladislav Kurenkov
Sergey Kolesnikov
CORL: Research-oriented Deep Offline Reinforcement Learning Library
NeurIPS 2023
Подробнее
Vladislav Kurenkov
Alexander Nikulin
Denis Tarasov
Sergey Kolesnikov
Alexander Nikulin
Denis Tarasov
Sergey Kolesnikov
Katakomba: Tools and Benchmarks for Data-Driven NetHack
NeurIPS 2023
Подробнее
Maksim Zhdanov
Ivan Karpukhin
Ivan Karpukhin
Catching Image Retrieval Generalization
Preprint
Подробнее
Alexander Nikulin
Vladislav Kurenkov
Denis Tarasov
Sergey Kolesnikov
Vladislav Kurenkov
Denis Tarasov
Sergey Kolesnikov
Anti-Exploration by Random Network Distillation
ICML 2023
Подробнее
Sofia Maria Lo Cicero Vaina
Nikita Balagansky
Daniil Gavrilov
Nikita Balagansky
Daniil Gavrilov
Diffusion Language Models Generation Can Be Halted Early
Preprint
Подробнее
Daniil Gavrilov
Nikita Balagansky
Nikita Balagansky
Ahead-of-Time P-Tuning
Preprint
Подробнее
Alexander Nikulin
Vladislav Kurenkov
Ilya Zisman
Artem Agarkov
Viacheslav Sinii
Sergey Kolesnikov
Vladislav Kurenkov
Ilya Zisman
Artem Agarkov
Viacheslav Sinii
Sergey Kolesnikov
XLand-MiniGrid: Scalable Meta-Reinforcement Learning Environments in JAX
NeurIPS 2023
Подробнее
Intrinsically Motivated Open-ended Learning Workshop
Vladislav Kurenkov
Sergey Kolesnikov
Sergey Kolesnikov
Showing Your Offline Reinforcement Learning Work: Online Evaluation Budget Matters
ICML 2022
Подробнее
Nikita Balagansky
Daniil Gavrilov
Daniil Gavrilov
PALBERT: Teaching ALBERT to Ponder
NeurIPS 2022
Подробнее
Ivan Karpukhin
Stanislav Dereka
Sergey Kolesnikov
Stanislav Dereka
Sergey Kolesnikov
Probabilistic Embeddings Revisited
Preprint
Подробнее
Mark Rofin
Nikita Balagansky
Daniil Gavrilov
Nikita Balagansky
Daniil Gavrilov
Linear Interpolation In Parameter Space is Good Enough for Fine-Tuned Language Models
Preprint
Подробнее
Stanislav Dereka
Ivan Karpukhin
Sergey Kolesnikov
Ivan Karpukhin
Sergey Kolesnikov
Deep Image Retrieval is not Robust to Label Noise
CVPR 2022
Подробнее
Open-Domain Reasoning Under Multi-Modal Settings Workshop
Denis Tarasov
Vladislav Kurenkov
Sergey Kolesnikov
Vladislav Kurenkov
Sergey Kolesnikov
Prompts and Pre-Trained Language Models for Offline Reinforcement Learning
ICLR 2022
Подробнее
Workshop on Generalizable Policy Learning in Physical World
Askhat Sitdikov
Nikita Balagansky
Daniil Gavrilov
Alexander Markov
Nikita Balagansky
Daniil Gavrilov
Alexander Markov
Classifiers are Better Experts for Controllable Text Generation
ACL 2022
Подробнее
Workshop on Transfer Learning for Natural Language Processing
Ivan Karpukhin
Stanislav Dereka
Sergey Kolesnikov
Stanislav Dereka
Sergey Kolesnikov
EXACT: How to Train Your Accuracy
ICML 2022
Подробнее
Topology, Algebra, and Geometry in Machine Learning Workshop
Alexander Nikulin
Vladislav Kurenkov
Denis Tarasov
Dmitry Akimov
Sergey Kolesnikov
Vladislav Kurenkov
Denis Tarasov
Dmitry Akimov
Sergey Kolesnikov
Q-Ensemble for Offline RL: Don't Scale the Ensemble, Scale the Batch Size
NeurIPS 2022
Подробнее
Offline RL Workshop
Dmitriy Akimov
Vladislav Kurenkov
Alexander Nikulin
Denis Tarasov
Sergey Kolesnikov
Vladislav Kurenkov
Alexander Nikulin
Denis Tarasov
Sergey Kolesnikov
Let Offline RL Flow: Training Conservative Agents in the Latent Space of Normalizing Flows
NeurIPS 2022
Подробнее
Offline RL Workshop
Наши работы
Omut AI наследует исследовательскую команду T-Bank Research, в которой мы занимаемся созданием новых алгоритмов в AI
2024
2023
2022
Образовательные услуги оказываются АНО ВО «Центральный университет», свидетельство № А007−115−77/1 039 609, 29 января 2024
Абитуриентам
Университет
Будьте в курсе первыми