RUBATO paper: decoupled clocks let full-duplex models think at full speed
EliasEskin · x · 2026-10-22
A new paper, "RUBATO: Decoupled Clocks Allow Full-Duplex Models to Think as Fast as They Can," points out that current full-duplex models tie their thinking to the conversation's pace, so reasoning speed is limited by speech.
RUBATO decouples the two, giving each stream its own clock so that thinking runs as fast as the hardware allows rather than at the real-time rhythm of the dialogue.
More from Research
- Going Meta dives into ontologies and graph semantics for production knowledge graphs — JeremyCMorgan · 2026-10-22
- Cohere's Rachad Alao on how open science underpins transparent, secure foundation models — PyTorch · 2026-10-22
- Four Gemini agents beat Minecraft's Ender Dragon in 27 hours — dying 605 times — krishnan · 2026-10-22
- Ropedia W0: a world model learning loco-manipulation from 10k hours of human egocentric video — _akhaliq · 2026-10-22
- Stanford colloquium on AI in oncology features senior author of Nature paper on autonomous medical AI agents — jonc101x · 2026-10-22
- UofT paper AREa: adaptive receptive-field attention for efficient high-res diffusion transformers — CSProfKGD · 2026-10-22