Interaction Models: A Scalable Approach to Human-AI Collaboration - Thinking Machines Lab

Interaction models move beyond turn-based AI interfaces by handling multimodal, real-time collaboration natively across audio, video, and text.

Today, we’re announcing a research preview of interaction models: models that handle interaction natively rather than through external scaffolding. We think interactivity should scale alongside intelligence; the way we work with AI should not be treated as an afterthought. Interaction models let people collaborate with AI the way we naturally collaborate with each other—they continuously take in audio, video, and text, and think, respond, and act in real time. We train an interaction model from scratch. To ensure real-time responsiveness, we adopt a multi-stream, micro-turn design. Our researc

saved by

• Jaclyn
• Elizabeth Qiu
• Ratan Kaliani
• Emma Guo
• Samuel Lo
• Rishi Kothari
• anka hu
• Information Flow
• Uzay Girit
• Thu Than
• Lydia Nottingham
• Jirat C

related reading

• Announcing Interactivity Research Grants - Thinking Machines Labthinkingmachines.ai
• Tiny Interaction Models - Rajan Agarwalrajan.sh
• Today, we are releasing a research preview of our user model, along with a set of evaluations designed to measure how faithfully user models capture human behavior.persimmon.humansand.ai
• The Future Worth Building Is Human - Thinking Machines Labthinkingmachines.ai
• Inkling: Our Open-Weights Model - Thinking Machines Labthinkingmachines.ai
• Ultra Instinct | Eric Jangevjang.com
• Advancing voice intelligence with new models in the API | OpenAIopenai.com
• Crossing the uncanny valley of conversational voice | Sesamesesame.com
• Improving Composer through real-time RL · Cursorcursor.com
• Using Artificial Intelligence to Augment Human Intelligencedistill.pub
• Real-Time Action Chunking with Large Modelspi.website
• M*: A Modular, Extensible, Serving System for Multimodal Modelsai.stanford.edu