POLAR formulates joint LoRA adapter caching and routing as a two-timescale contextual bandit, achieving sublinear regret bounds and outperforming non-adaptive baselines in experiments with real adapters.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
Distilling LLM perplexity-based utility signals into bi-encoder embeddings via a Utility-Modulated InfoNCE loss yields 30%+ Recall@1 gains over BGE-Base at 180x the speed of LLM re-ranking.
citing papers explorer
No citing papers match the current filters.