Local Prototype Reconstruction for Text-Compatible Speech-to-LLM Bridge Pretraining
arXiv:2610.11159v1 Announce Type: new Abstract: Speech-to-LLM systems often connect a frozen speech encoder to a frozen large language model (LLM) through a small trainable bridge. The bridge is usually treated as plumbing, but it in fact defines the geometry of the speech-to-LLM interface, and the…
Read the full story at arXiv cs.CL ↗
Timeline · 1 report
- 2026-10-09 04:00 · arXiv cs.CL
Local Prototype Reconstruction for Text-Compatible Speech-to-LLM Bridge Pretraining