← Back to research

Research Brief · 2026-10-08 Core

EgoVoice: Proactive Spoken Assistance from Egocentric Multimodal Streams

The idea, in brief

Train MiniCPM-o 4.5 to choose Listen or Speak on egocentric audio/video. SFT + DPO refines timing and restraint under a supplied task recipe.

Editorial summary · not the author abstract. Read the linked paper for the complete abstract and claims.
EgoVoice first-person multimodal stream, silence or intervention decision and spoken guidance
EgoVoice first-person multimodal stream, silence or intervention decision and spoken guidance Original figure · paper authors ↗

Release evidence

Official project page schedules code, models and data for November 2026. A base-model release is not an EgoVoice checkpoint release.

Last checked · 2026-10-24