BWhat changed
Trained a full-duplex model to trigger selective asynchronous retrieval and incorporate textual references during the gap between response onset and key information delivery.
Scientific scope
Trained a full-duplex model to trigger selective asynchronous retrieval and incorporate textual references during the gap between response onset and key information delivery. Inherits Moshi and retrieval-augmented generation. Timing depends on bounded-latency back ends and conversational gaps; retrieval is neither free nor a guarantee of factuality. Mathematical-task gains are tool-assisted model evaluations, not new mathematical discoveries.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Inherits Moshi and retrieval-augmented generation. Timing depends on bounded-latency back ends and conversational gaps; retrieval is neither free nor a guarantee of factuality. Mathematical-task gains are tool-assisted model evaluations, not new mathematical discoveries.
Contributors
- Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
- MoshiRAG: Asynchronous Knowledge Retrieval for Full-Duplex Speech Language Models
- Kyutai scientific publications index
Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.
Full scientific record · Browse contribution grades · Request a correction