Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Structure Aware Neural Architecture Search for Mixture of Experts
Petr Babkin, Oleg Bakhteev
Neural Architecture Search (NAS) has so far rarely been applied to Mixture-of-Experts (MoE) models, and existing MoE designs leave the alignment between experts and the structure o…
cs.LG2026
Surrogate assisted diversity estimation in neural ensemble search
Alexandr Udeneev, Petr Babkin, Oleg Bakhteev
Ensembles are a standard way to improve the performance and robustness of deep neural networks, but their effectiveness crucially depends on both the quality and the diversity of i…
cs.LG2025
Towards Effectively Leveraging Execution Traces for Program Repair with Code LLMs
Mirazul Haque, Petr Babkin, Farima Farmahinifarahani +1
Large Language Models (LLMs) show promising performance on various programming tasks, including Automatic Program Repair (APR). However, most approaches to LLM-based APR are limite…