Mikhail Salnikov

NAS-Bench-NLP: Neural Architecture Search Benchmark for Natural Language Processing

2022 · IEEE Access

Neural Architecture Search (NAS) is a promising and rapidly evolving research area. Training a large number of neural networks requires an exceptional amount of computational power, which makes NAS unreachable for those researchers who have …

Adaptive Retrieval Without Self-Knowledge? Bringing Uncertainty Back Home

2025 · arXiv (Cornell University)

Retrieval Augmented Generation (RAG) improves correctness of Question Answering (QA) and addresses hallucinations in Large Language Models (LLMs), yet greatly increase computational costs. Besides, RAG is not always needed as may introduce irrelevant information. Recent …