Institution profile

JetBrains

Industry researcheurope · cz
Official website
Research library86linked papers
Opportunities0open roles
Selected work

Representative Papers

The Design Space of in-IDE Human-AI Experience

Oct 11, 2024arXiv.org

Current AI assistant features in IDEs exhibit a significant misalignment with developers’ authentic needs, necessitating a systematic understanding of heterogeneous user requirements. Method: We conducted semi-structured interviews with 35 practitioners—comprising AI adopters, attriters, and non-users—to empirically construct the first human-AI interaction design space for IDE-integrated AI assistants. Through thematic coding and cross-cohort comparative analysis, we identified fundamental divergences across user groups along five dimensions: reliability, privacy, personalization, proactivity, and ethical concerns. Contribution/Results: We propose a role-driven, five-dimensional design framework—encompassing technical robustness, interaction modality, goal alignment, skill abstraction, and cognitive offloading—alongside 12 actionable design guidelines. This work advances IDE AI tools toward greater reliability, contextual awareness, privacy-by-design, and seamless workflow integration.

4 citationsRead paper

On Pretraining for Project-Level Code Completion

Oct 15, 2025

This study investigates how warehouse-level code processing strategies affect the in-context learning capability of OpenCoder for project-level code completion. Methodologically, we pretrain a 1.5B-parameter OpenCoder on only 1 billion tokens of warehouse-scale code, extend its context window to 16,384 tokens, and systematically optimize the RoPE scaling parameter. Our key findings are: (i) RoPE scaling optimization is the primary driver of performance gains; and (ii) lightweight file-level training retains high effectiveness for short sequences while substantially reducing computational and data requirements. Empirical evaluation on the Long Code Arena benchmark shows that our approach achieves performance comparable to models trained on tens of billions of tokens. This work establishes a new paradigm for efficient, low-resource project-level code completion—demonstrating that carefully engineered architectural and positional-encoding adjustments can compensate for limited pretraining scale without sacrificing contextual reasoning capability.

2 citations1 influentialRead paper
Recent publications

Latest Papers

Improved Quantum Algorithms for Subset Sum and $k$-SUM

Aug 07, 2026

This work addresses the worst-case quantum complexity bottlenecks of Subset Sum and its parameterized variant, the k-SUM problem. The authors propose a novel quantum search framework that integrates quantum walks, block reduction, and a refined modular-7 classification scheme. By leveraging structured subproblem decomposition and an improved search strategy, they achieve the first faster worst-case quantum algorithm for instances where \(k \equiv 3\) or \(6 \pmod{7}\), attaining a time complexity of \(\tilde{O}(n^{\Psi_k})\). Extending this approach to the general Subset Sum problem yields a quantum algorithm with complexity \(O^*(2^{2n/7})\), surpassing the previous best-known bound of \(O^*(2^{n/3})\).

0 citationsRead paper

If Edge Coloring is Hard under SETH, then SETH is False

Jul 23, 2026

This work investigates whether strong exponential time lower bounds for the edge-coloring problem can be established under mainstream complexity assumptions such as the Strong Exponential Time Hypothesis (SETH), 3-SUM, or APSP, thereby explaining the longstanding absence of efficient algorithms for this problem. Through refined reductions and proof-by-contradiction arguments, the study demonstrates for the first time that if any of these hypotheses implied a lower bound of the form α^{n²} for edge coloring, the hypotheses themselves would be invalidated. This result reveals a fundamental logical inconsistency between the presumed hardness of edge coloring and these core complexity conjectures, thereby ruling out the feasibility of proving such strong lower bounds via conventional reduction techniques and challenging the prevailing paradigms in fine-grained complexity for graph coloring problems.

0 citationsRead paper