analiza aiqbench
This arXiv preprint proposes RUBATO, a positional encoding that gives each internal "thinking" stream its own clock, so a speech full-duplex model can run at whatever decoding speed the hardware allows. The reported gains are benchmark results on spoken reasoning tasks (e.g., Spoken GSM8K, BIG-Bench Audio) and rest on the authors' own evaluations, which have not been independently replicated. For readers, the practical point is that training on two extreme decoding speeds and generalizing zero-shot to intermediate rates could simplify building latency-adaptive voice assistants.
RUBATO: Decoupled Clocks Allow Full-Duplex Models to Think as Fast as They Can
arXiv:2610.14299v1 Announce Type: cross Abstract: Recent Speech Full-Duplex (FDX) models are capable of engaging in naturalistic conversation by listening and speaking at the same time. Building on this foundation, recent architectures introduce internal thinking streams to enhance their intelligence. To guarantee these streams process successfully in real time, existing methods enforce a fixed decoding rate, which assumes a hardware profile capable of a specific latency. We argue this static approach is severely suboptimal. Because internal thinking is intrinsically asynchronous, an ideal FDX model should sustain real-time conversational flow while allowing each stream to decode at its own hardware-adaptive rate. Thinking streams must process as fast as the hardware allows to deliver accurate answers faster. To solve this, we propose RUBATO, a novel multistream positional encoding that assigns independent clocks to entirely decouple the streams. This structural isolation empowers the model to zero-shot interpolate across any inference decoding speed. It drastically simplifies dataset construction by requiring training on only two extreme decoding speeds while smoothly adapting to any intermediate rate during deployment. RUBATO demonstrates consistent robustness across five spoken reasoning tasks. On Spoken GSM8K, a baseline model collapses to 1.7% accuracy at interpolated speeds. Conversely, RUBATO-Full sustains 48.7% to 51.1% accuracy across all rates, leveraging faster hardware to achieve a 6.5x shorter time-to-answer with a constant time-to-first-response. This advantage holds on BIG-Bench Audio and amplifies significantly during complex full-duplex interruptions. Specifically, when a user interjects while the model is actively speaking and reasoning, RUBATO-Full achieves 40.0% to 45.1% accuracy, whereas the baseline fails completely.
Abstract:Recent Speech Full-Duplex (FDX) models are capable of engaging in naturalistic conversation by listening and speaking at the same time. Building on this foundation, recent architectures introduce internal thinking streams to enhance their intelligence. To guarantee these streams process successfully in real time, existing methods enforce a fixed decoding rate, which assumes a hardware profile capable of a specific latency. We argue this static approach is severely suboptimal. Because internal thinking is intrinsically asynchronous, an ideal FDX model should sustain real-time conversational flow while allowing each stream to decode at its own hardware-adaptive rate. Thinking streams must process as fast as the hardware allows to deliver accurate answers faster. To solve this, we propose RUBATO, a novel multistream positional encoding that assigns independent clocks to entirely decouple the streams. This structural isolation empowers the model to zero-shot interpolate across any inference decoding speed. It drastically simplifies dataset construction by requiring training on only two extreme decoding speeds while smoothly adapting to any intermediate rate during deployment. RUBATO demonstrates consistent robustness across five spoken reasoning tasks. On Spoken GSM8K, a baseline model collapses to 1.7% accuracy at interpolated speeds. Conversely, RUBATO-Full sustains 48.7% to 51.1% accuracy across all rates, leveraging faster hardware to achieve a 6.5x shorter time-to-answer with a constant time-to-first-response. This advantage holds on BIG-Bench Audio and amplifies significantly during complex full-duplex interruptions. Specifically, when a user interjects while the model is actively speaking and reasoning, RUBATO-Full achieves 40.0% to 45.1% accuracy, whereas the baseline fails completely.
Audio and Speech Processing (eess.AS); Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Sound (cs.SD)
arXiv:2610.14299 [eess.AS]
(or arXiv:2610.14299v1 [eess.AS] for this version)
https://doi.org/10.48550/arXiv.2610.14299 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 353 cuvinte
Subiecte conexe
Links #5: 2026/07
LessWrong · 31 iul. 2026
News
Quantum Computing Report · 25 iul. 2026
Latent reasoning architectures would likely undermine CoT, our strongest oversight tool
AI Alignment Forum · 23 sept. 2026
Act First, Reason Later: Accelerating On-Policy Distillation for Multi-Turn Agents via Reference-Conditioned Inverse Dynamics
arXiv · 1 oct. 2026