SOURCE-LINKED INTELLIGENCE

Omni-Streaming Thinking

arXiv · AI, language, vision and robotics · article · Sep 14, 2026 · UTC

Streaming omni-modal models must decide what and when to answer from the video chunks and synchronized audio observed so far. Visual cues often support an interpretation before an utterance or sound event is complete. If that interpretation enters memory as a fact, later reasoning can keep relaying it even after audio contradicts it. We call this failure premature cross-modal commitment. We propose Omni-Streaming Thinking (OST), which generates structured outputs that include evidence observed so far, forecasts of future evidence, and claims based on this evidence. Each claim is initially mark

Read original source ↗ Open in workspace

recordType

paper

region

Global