Spoken Dialogue Models (SDMs) typically share a speech-token space for generation and synthesis, leading to long autoregressive sequences and costly inference. Lower-rate speech tokenizers shorten seq
CoSTA decouples generation and synthesis token spaces to accelerate spoken dialogue models while preserving quality and compatibility.
Spoken Dialogue Models (SDMs) typically share a speech-token space for generation and synthesis, leading to long autoregressive sequences and costly inference. Lower-rate speech tokenizers shorten sequences but may introduce compression-quality trade-offs and costly replacement without breaking this coupling. To address this limitation, we propose CoSTA, a compatibility-preserving post-hoc framework that decouples generation and synthesis token spaces while retaining the original speech tokenizer and decoder. CoSTA extends the generation token space with compressed representations via mean-initialized vocabulary extension, pronunciation adaptation, and dialogue adaptation, followed by…
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.
CoSTA: Compressed Speech Token Adaptation for Efficient Spoken Dialogue Models was first seen on Hugging Face · Daily papers on Oct 30, 2026. Since then it has appeared in 37 checks on 4 different days. Its best position was #19 of 30, reached on Oct 30, 19:28 UTC. It dropped off the list after Nov 2, 09:28 UTC.
Position on Hugging Face · Daily papers at every check (lower is better).
Best rank per day (UTC).
Platform metric as reported by Hugging Face.
Archived daily, weekly and monthly lists that include this entry.
Not at the moment. It was last on the list on Nov 2, 09:28 UTC, after 4 days of trending.
#19 on Hugging Face · Daily papers, on Oct 30, 19:28 UTC. Trendoday checks this list every 120 minutes.
It was first seen on Oct 30, 2026 and has been on the list on 4 days (37 checks) since.