collaborators

7 papers

cs.LG2026

Don't Claim Benchmark-Oriented Optimization Improves General Coding Capability -- Diverse Evaluation Is Required

Egor Shibaev, Vera Kudrevskaia, Timur Galimzyanov +9

Post-training papers, model cards, and blog posts often treat scores on a small set of coding benchmarks (e.g., SWE-bench and LiveCodeBench) as evidence of broad coding capability,…

cs.SE2026

Attention Mechanism and Heuristic Approach: Context-Aware File Ranking Using Multi-Head Self-Attention

Pradeep Kumar Sharma, Shantanu Godbole, Sarada Prasad Jena +1

The identification and ranking of impacted files within software reposi-tories is a key challenge in change impact analysis. Existing deterministic approaches that combine heuristi…

cs.SE2025

Keeping Code-Aware LLMs Fresh: Full Refresh, In-Context Deltas, and Incremental Fine-Tuning

Pradeep Kumar Sharma, Ishaan Puri, Mantinder Jit Singh +2

Modern codebases evolve continuously: files are renamed or deleted; public APIs drift; behavior shifts within otherwise familiar modules. A model trained yesterday to map a develop…

cs.AI2025

Scalable and Explainable Enterprise Knowledge Discovery Using Graph-Centric Hybrid Retrieval

Nilima Rao, Jagriti Srivastava, Pradeep Kumar Sharma +1

Modern enterprises manage vast knowledge distributed across heterogeneous systems such as Jira, Git repositories, Confluence, and wikis. Conventional retrieval methods based on key…

cs.SE2025

Vector Graph-Based Repository Understanding for Issue-Driven File Retrieval

Kostiantyn Bevziuk, Andrii Fatula, Svetozar Lashin Yaroslav Opanasenko +3

We present a repository decomposition system that converts large software repositories into a vectorized knowledge graph which mirrors project architectural and semantic structure,…

cs.AR2025

Production-Grade Local LLM Inference on Apple Silicon: A Comparative Study of MLX, MLC-LLM, Ollama, llama.cpp, and PyTorch MPS

Varun Rajesh, Om Jodhpurkar, Pooja Anbuselvan +5

We present a systematic, empirical evaluation of five local large language model (LLM) runtimes on Apple Silicon: MLX, MLC-LLM, llama.cpp, Ollama, and PyTorch MPS. Experiments were…