activity
20242026
collaborators

5 papers

cs.AI2026

Self-Guided Plan Extraction for Instruction-Following Tasks with Goal-Conditional Reinforcement Learning

Zoya Volovikova, Nikita Sorokin, Dmitriy Lukashevskiy +2

We introduce SuperIgor, a framework for instruction-following tasks. Unlike prior methods that rely on predefined subtasks, SuperIgor enables a language model to generate and refin…

cs.LG2026

Not All Denoising Steps Are Equal: Model Scheduling for Faster Masked Diffusion Language Models

Ivan Sedykh, Nikita Sorokin, Valentin Malykh

Recent advances in masked diffusion language models (MDLMs) narrow the quality gap to autoregressive LMs, but their sampling remains expensive because generation requires many full…

cs.CL2026

Hierarchical Embedding Fusion for Retrieval-Augmented Code Generation

Nikita Sorokin, Ivan Sedykh, Valentin Malykh

Retrieval-augmented code generation often conditions the decoder on large retrieved code snippets. This ties online inference cost to repository size and introduces noise from long…

cs.CL2025

Iterative Self-Training for Code Generation via Reinforced Re-Ranking

Nikita Sorokin, Ivan Sedykh, Valentin Malykh

Generating high-quality code that solves complex programming tasks is challenging, especially with current decoder-based models that produce highly stochastic outputs. In code gene…

cs.CL2024

CCT-Code: Cross-Consistency Training for Multilingual Clone Detection and Code Search

Anton Tikhonov, Nikita Sorokin, Dmitry Abulkhanov +3

We consider the well-known and important tasks of clone detection and information retrieval for source code. The most standard setup is to search clones inside the same language co…