On September 6, 2026, MaAI said its English VAP model was trained on a larger scale of data. The project predicts conversational cues and head movements in real time.
On September 6, 2026, MaAI said its English VAP model was trained on a larger scale of data, without specifying the size of the increase. The linked project describes real-time software for predicting turn-taking, backchannel cues, and head movements.
Engineers working on real-time interaction can consult the announcement and original project to assess the updated model. Check the original materials for the stated scope and results; the report provides no metrics or quantitative details about the update.