Beyond Answering: Learning to Speak First and Act in Streaming Video Researchers introduced AURA 2.0, a streaming video large language model that adds three core upgrades to the original AURA, enabling it to speak first and act on events in a video stream rather than waiting for user prompts. The model targets the gap left by most AI assistants, which stay silent even when events in the video stream offer meaningful opportunities for conversation. Most AI assistants respond only when prompted, remaining silent even when events in the video stream offer meaningful opportunities for conversation. To move beyond purely user-driven interaction, we present AURA 2.0, a streaming video large language model that introduces three core upgrades to AURA