35 citations · 140 across the 24 of their papers we have counts for
24 papers
SDG-MoE: Signed Debate Graph Mixture-of-Experts
Stepan Kulibaba, Kirill Labzin, Artem Dzhalilov +4
Sparse MoE models achieve a good balance between capacity and compute by routing each token to a small subset of experts. However, in most MoE architectures, once a token is routed…
KompeteAI: Accelerated Autonomous Multi-Agent System for End-to-End Pipeline Generation for Machine Learning Problems
Stepan Kulibaba, Artem Dzhalilov, Roman Pakhomov +3
Recent Large Language Model (LLM)-based AutoML systems demonstrate impressive capabilities but face significant limitations such as constrained exploration strategies and a severe…
Data-Driven Short-Term Daily Operational Sea Ice Regional Forecasting
Timofey Grigoryev, Polina Verezemskaya, Mikhail Krinitskiy +9
Global warming made the Arctic available for marine operations and created demand for reliable operational sea ice forecasts to make them safe. While ocean-ice numerical models are…
Traffic4cast at NeurIPS 2021 -- Temporal and Spatial Few-Shot Transfer Learning in Gridded Geo-Spatial Processes
Christian Eichenberger, Moritz Neun, Henry Martin +34
The IARAI Traffic4cast competitions at NeurIPS 2019 and 2020 showed that neural networks can successfully predict future traffic conditions 1 hour into the future on simply aggrega…
Self-Imitation Learning from Demonstrations
Georgiy Pshikhachev, Dmitry Ivanov, Vladimir Egorov +1
Despite the numerous breakthroughs achieved with Reinforcement Learning (RL), solving environments with sparse rewards remains a challenging task that requires sophisticated explor…
Improving State-of-the-Art in One-Class Classification by Leveraging Unlabeled Data
Farid Bagirov, Dmitry Ivanov, Aleksei Shpilman
When dealing with binary classification of data with only one labeled class data scientists employ two main approaches, namely One-Class (OC) classification and Positive Unlabeled…
MineRL Diamond 2021 Competition: Overview, Results, and Lessons Learned
Anssi Kanervisto, Stephanie Milani, Karolis Ramanauskas +19
Reinforcement learning competitions advance the field by providing appropriate scope and support to develop solutions toward a specific problem. To promote the development of more…
Simple End-to-end Deep Learning Model for CDR-H3 Loop Structure Prediction
Natalia Zenkova, Ekaterina Sedykh, Tatiana Shugaeva +3
Predicting a structure of an antibody from its sequence is important since it allows for a better design process of synthetic antibodies that play a vital role in the health indust…
Maximum Entropy Model-based Reinforcement Learning
Oleg Svidchenko, Aleksei Shpilman
Recent advances in reinforcement learning have demonstrated its ability to solve hard agent-environment interaction tasks on a super-human level. However, the application of reinfo…
Solving Traffic4Cast Competition with U-Net and Temporal Domain Adaptation
Vsevolod Konyakhin, Nina Lukashina, Aleksei Shpilman
In this technical report, we present our solution to the Traffic4Cast 2021 Core Challenge, in which participants were asked to develop algorithms for predicting a traffic state 60…
Flatland Competition 2020: MAPF and MARL for Efficient Train Coordination on a Grid World
Florian Laurent, Manuel Schneider, Christian Scheller +24
The Flatland competition aimed at finding novel approaches to solve the vehicle re-scheduling problem (VRSP). The VRSP is concerned with scheduling trips in traffic networks and th…
Balancing Rational and Other-Regarding Preferences in Cooperative-Competitive Environments
Dmitry Ivanov, Vladimir Egorov, Aleksei Shpilman
Recent reinforcement learning studies extensively explore the interplay between cooperative and competitive behaviour in mixed environments. Unlike cooperative environments where a…
End-to-end Deep Object Tracking with Circular Loss Function for Rotated Bounding Box
Vladislav Belyaev, Aleksandra Malysheva, Aleksei Shpilman
The task object tracking is vital in numerous applications such as autonomous driving, intelligent surveillance, robotics, etc. This task entails the assigning of a bounding box to…
MAGNet: Multi-agent Graph Network for Deep Multi-agent Reinforcement Learning
Aleksandra Malysheva, Daniel Kudenko, Aleksei Shpilman
Over recent years, deep reinforcement learning has shown strong successes in complex single-agent tasks, and more recently this approach has also been applied to multi-agent domain…
Deep Learning of Cell Classification using Microscope Images of Intracellular Microtubule Networks
Aleksei Shpilman, Dmitry Boikiy, Marina Polyakova +3
Microtubule networks (MTs) are a component of a cell that may indicate the presence of various chemical compounds and can be used to recognize properties such as treatment resistan…
Learning to Run with Potential-Based Reward Shaping and Demonstrations from Video Data
Aleksandra Malysheva, Daniel Kudenko, Aleksei Shpilman
Learning to produce efficient movement behaviour for humanoid robots from scratch is a hard problem, as has been illustrated by the "Learning to run" competition at NIPS 2017. The…
A comparative evaluation of machine learning methods for robot navigation through human crowds
Anastasia Gaydashenko, Daniel Kudenko, Aleksei Shpilman
Robot navigation through crowds poses a difficult challenge to AI systems, since the methods should result in fast and efficient movement but at the same time are not allowed to co…
Continuous Gesture Recognition from sEMG Sensor Data with Recurrent Neural Networks and Adversarial Domain Adaptation
Ivan Sosin, Daniel Kudenko, Aleksei Shpilman
Movement control of artificial limbs has made big advances in recent years. New sensor and control technology enhanced the functionality and usefulness of artificial limbs to the p…
Solving Black-Box Optimization Challenge via Learning Search Space Partition for Local Bayesian Optimization
Mikita Sazanovich, Anastasiya Nikolskaya, Yury Belousov +1
Black-box optimization is one of the vital tasks in machine learning, since it approximates real-world conditions, in that we do not always know all the properties of a given syste…
Lipophilicity Prediction with Multitask Learning and Molecular Substructures Representation
Nina Lukashina, Alisa Alenicheva, Elizaveta Vlasova +5
Lipophilicity is one of the factors determining the permeability of the cell membrane to a drug molecule. Hence, accurate lipophilicity prediction is an essential step in the devel…
Automatic generation of reviews of scientific papers
Anna Nikiforovskaya, Nikolai Kapralov, Anna Vlasova +2
With an ever-increasing number of scientific papers published each year, it becomes more difficult for researchers to explore a field that they are not closely familiar with alread…
Imitation Learning Approach for AI Driving Olympics Trained on Real-world and Simulation Data Simultaneously
Mikita Sazanovich, Konstantin Chaika, Kirill Krinkin +1
In this paper, we describe our winning approach to solving the Lane Following Challenge at the AI Driving Olympics Competition through imitation learning on a mixed set of simulati…
Artificial Intelligence for Prosthetics - challenge solutions
Łukasz Kidziński, Carmichael Ong, Sharada Prasanna Mohanty +47
In the NeurIPS 2018 Artificial Intelligence for Prosthetics challenge, participants were tasked with building a controller for a musculoskeletal model with a goal of matching a giv…
Deep Multi-Agent Reinforcement Learning with Relevance Graphs
Aleksandra Malysheva, Tegg Taekyong Sung, Chae-Bong Sohn +2
Over recent years, deep reinforcement learning has shown strong successes in complex single-agent tasks, and more recently this approach has also been applied to multi-agent domain…