3 citations · 5 across the 5 of their papers we have counts for
7 papers
Coding-Agent Benchmarks Should Match Their Users' Task Flows
Igor Slinko, Yaroslav Golubev, Sergey Titov
The evaluation of coding agents generally strives to be as realistic as possible. In our study, we collect 4,782 agent sessions of real software engineers in JetBrains IDEs, which…
On Problems of Implicit Context Compression for Software Engineering Agents
Kirill Gelvan, Igor Slinko, Felix Steinbauer +3
LLM-based Software Engineering agents face a critical bottleneck: context length limitations cause failures on complex, long-horizon tasks. One promising solution is to encode cont…
Step Rejection Fine-Tuning: A Practical Distillation Recipe
Igor Slinko, Ilia Zavidnyi, Egor Bogomolov +1
Rejection Fine-Tuning (RFT) is a standard method for training LLM agents, where unsuccessful trajectories are discarded from the training set. In the context of SWE-bench tasks, th…
The Complexity Trap: Simple Observation Masking Is as Efficient as LLM Summarization for Agent Context Management
Tobias Lindenbauer, Igor Slinko, Ludwig Felder +2
Large Language Model (LLM)-based agents solve complex tasks through iterative reasoning, exploration, and tool-use, a process that can result in long, expensive context histories.…
Training Deep SLAM on Single Frames
Igor Slinko, Anna Vorontsova, Dmitry Zhukov +2
Learning-based visual odometry and SLAM methods demonstrate a steady improvement over past years. However, collecting ground truth poses to train these methods is difficult and exp…
DISCOMAN: Dataset of Indoor SCenes for Odometry, Mapping And Navigation
Pavel Kirsanov, Airat Gaskarov, Filipp Konokhov +7
We present a novel dataset for training and benchmarking semantic SLAM methods. The dataset consists of 200 long sequences, each one containing 3000-5000 data frames. We generate t…
Scene Motion Decomposition for Learnable Visual Odometry
Igor Slinko, Anna Vorontsova, Filipp Konokhov +2
Optical Flow (OF) and depth are commonly used for visual odometry since they provide sufficient information about camera ego-motion in a rigid scene. We reformulate the problem of…