Learning to Route LLMs from Bandit Feedback: One Policy, Many Trade-offs
Wang Wei, Tiankai Yang, H Chen, Zhao, Yue, Franck Dernoncourt, Ryan A. Rossi, Hoda Eldardiry
Who it is from
- Dolbyaffiliation declared by the authors, according to OpenAlex
Other papers from the same organizations
- V2A-Mapper: A Lightweight Solution for Vision-to-Audio Generation by Connecting Foundation ModelsDolby · 104 citations
- GASS: Generalizing Audio Source Separation with Large-Scale DataDolby · 28 citations
- Diff-SAGe: End-to-End Spatial Audio Generation Using Diffusion ModelsDolby · 27 citations
- A Generic Framework for Conformal FairnessDolby · 18 citations
- Sequential Contrastive Audio-Visual LearningDolby · 17 citations
- Gotta Hear Them All: Towards Sound Source Aware Audio GenerationDolby · 15 citations