Multimodality · 2026
Interaction Models: A Scalable Approach to Human-AI Collaboration
Replaces discrete turn-taking with a time-aligned ~200ms 'micro-turn' architecture over continuous audio/video/text streams, enabling simultaneous speech, interjections, and visual proactivity in a 276B MoE model.
Editorial record
Plain-language summary
Replaces discrete turn-taking with a time-aligned ~200ms 'micro-turn' architecture over continuous audio/video/text streams, enabling simultaneous speech, interjections, and visual proactivity in a 276B MoE model.
Knowledge graph
Relationships
Descendants
Conceptual ancestorEvidence: Strongly supported
Native/Omni Multimodality (Gemini / GPT-4V / GPT-4o)
Extends native multimodal models to continuous real-time interaction
TML
Source record
Provenance
- Record ID
- P-660
- Record created
- 2026-07-13
- Last reviewed
- 2026-07-14
- Record version
- 2
Citation caveat: Citation metadata is approximate and marked unverified in the source dataset.