| 2026 | ACL | Self-Guided Plan Extraction for Instruction-Following Tasks with Goal-Conditional Reinforcement Learning. | Zoya Volovikova, Nikita Sorokin, Dmitriy Lukashevskiy, Aleksandr Panov, Alexey Skrynnik |
| 2026 | SIGIR | SAGE: Solver-Aligned Guided Exploration. | Nikita Sorokin, Ivan Sedykh, Timur Ionov, Valentin Malykh |
| 2026 | SIGIR | Hierarchical Embedding Fusion for Retrieval-Augmented Code Generation. | Nikita Sorokin, Ivan Sedykh, Valentin Malykh |
| 2025 | ECIR | Iterative Self-training for Code Generation via Reinforced Re-ranking. | Nikita Sorokin, Ivan Sedykh, Valentin Malykh |
| 2025 | NAACL | CCT-Code: Cross-Consistency Training for Multilingual Clone Detection and Code Search. | Nikita Sorokin, Tikhonov Anton, Dmitry Abulkhanov, Ivan Sedykh, Irina Piontkovskaya, Valentin Malykh |
| 2024 | COLING | Searching by Code: A New SearchBySnippet Dataset and SnippeR Retrieval Model for Searching by Code Snippets. | Ivan Sedykh, Nikita Sorokin, Dmitry Abulkhanov, Sergey I. Nikolenko, Valentin Malykh |
| 2023 | SIGIR | LAPCA: Language-Agnostic Pretraining with Cross-Lingual Alignment. | Dmitry Abulkhanov, Nikita Sorokin, Sergey I. Nikolenko, Valentin Malykh |
| 2022 | NAACL | Ask Me Anything in Your Native Language. | Nikita Sorokin, Dmitry Abulkhanov, Irina Piontkovskaya, Valentin Malykh |
| 2021 | RANLP | Multiple Teacher Distillation for Robust and Greener Models. | Artur Ilichev, Nikita Sorokin, Irina Piontkovskaya, Valentin Malykh |