Chunk-interleaved full-duplex speech language models listen and speak in fixed time chunks, and each chunk must be processed before the next one arrives. Their workload is asymmetric across chunks: li
A training-free, lossless speculative decoding framework exploits idle compute in chunk-interleaved full-duplex speech language models to draft and verify upcoming audio chunks, substantially reducing response and tool-call delays.
Chunk-interleaved full-duplex speech language models listen and speak in fixed time chunks, and each chunk must be processed before the next one arrives. Their workload is asymmetric across chunks: listen chunks leave compute idle while awaiting audio, and speak and tool-call chunks require serial generation, which delays responses and tool calls. Using the idle compute for the next chunk requires decoding it before its audio arrives, under an assumed input. Taking silence as the assumed input and comparing the output with the output under real audio on four models, we observe two properties. First, the next audio chunk does not change the output in 95.3% of chunks. Second, 88% of changes…
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.
Decode Before You Hear: Speculative Listening for Chunk-Interleaved Full-Duplex Speech Language Models was first seen on Hugging Face · Daily papers on Nov 6, 2026. Since then it has appeared in 28 checks on 3 different days. Its best position was #23 of 30, reached on Nov 6, 21:28 UTC. It is #26 right now, climbing from #28 to #26 over the last 6 checks.
Position on Hugging Face · Daily papers at every check (lower is better).
Best rank per day (UTC).
▲ as reported by Hugging Face.
Archived daily, weekly and monthly lists that include this entry.
Yes. As of Nov 8, 17:28 UTC it is #26, climbing from #28 to #26 over the last 6 checks.
#23 on Hugging Face · Daily papers, on Nov 6, 21:28 UTC. Trendoday checks this list every 120 minutes.
It was first seen on Nov 6, 2026 and has been on the list on 3 days (28 checks) since.