8 citations · 16 across the 7 of their papers we have counts for
5 papers · 1 filter
Blockwise Advantage Estimation for Multi-Objective RL with Verifiable Rewards
Kirill Pavlenko, Alexander Golubev, Simon Karasik +1
Group Relative Policy Optimization (GRPO) assigns a single scalar advantage to all tokens in a completion. For structured generations with explicit segments and objectives, this co…
Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement Learning
Alexander Golubev, Maria Trofimova, Sergei Polezhaev +9
Research on applications of reinforcement learning (RL) to large language models has mostly been focused on single-turn problems, such as mathematical reasoning or single-shot code…
Shifts: A Dataset of Real Distributional Shift Across Multiple Large-Scale Tasks
Andrey Malinin, Neil Band, Ganshin +17
There has been significant research done on developing methods for improving robustness to distributional shift and uncertainty estimation. In contrast, only limited work has exami…
PRANK: motion Prediction based on RANKing
Yuriy Biktairov, Maxim Stebelev, Irina Rudenko +2
Predicting the motion of agents such as pedestrians or human-driven vehicles is one of the most critical problems in the autonomous driving domain. The overall safety of driving an…
Fast Weak Learner Based on Genetic Algorithm
Boris Yangel
An approach to the acceleration of parametric weak classifier boosting is proposed. Weak classifier is called parametric if it has fixed number of parameters and, so, can be repres…