Pith. sign in

Optllm: Optimal assignment of queries to large language models

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.LG 1

years

2025 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

background 1

representative citing papers

One Head, Many Models: Cross-Attention Routing for Cost-Aware LLM Selection

cs.LG · 2025-09-11 · conditional · novelty 5.0

A single-head cross-attention router that jointly encodes the query and each candidate model improves cost-quality trade-offs on RouterBench by a few percent over KNN, MLP, and SVM baselines, though the headline gains are smaller than the abstract suggests.

citing papers explorer

Showing 1 of 1 citing paper.

  • One Head, Many Models: Cross-Attention Routing for Cost-Aware LLM Selection cs.LG · 2025-09-11 · conditional · none · ref 4

    A single-head cross-attention router that jointly encodes the query and each candidate model improves cost-quality trade-offs on RouterBench by a few percent over KNN, MLP, and SVM baselines, though the headline gains are smaller than the abstract suggests.