AURA 2.0 Adds Model-Initiated Conversations to Streaming Video LLMs
AURA 2.0 is a streaming video large language model that introduces Model-Initiated Conversation, allowing it to identify discussion-worthy topics in an evolving video stream and start interactions without a user query. It also adds Stream-Aware Tool Calling, Interactive Visual Grounding for user-marked objects and frame-aligned bounding boxes, and Long-Horizon Interaction Memory for contextual continuity. The model was trained with a dedicated streaming interaction dataset and a three-stage training scheme. The authors report leading performance among open-source streaming models on public benchmarks and open-source the model weights and inference code.
It documents a concrete open-source research advance toward proactive, tool-using video assistants rather than purely prompt-driven interaction.
Comments & Questions (0)
No comments yet
Be the first to comment!