AURA 2.0 released
The story so far
Hugging Face has released the streaming video large language model AURA 2.0, which can actively engage in dialogue, call tools, and achieve interactive visual localization, with long-term memory capabilities. Its core upgrades include model active dialogue (MIC), streaming perception tool calling (SATC), and interactive visual localization (IVG), enhancing streaming interaction through a three-stage training program. Public streaming benchmark tests show that AURA 2.0 performs leading among open-source models, with new interactive capabilities specifically evaluated and validated.
AI-written from the reports · Updated 12 hours ago
Coverage timeline
Follow the coverage to see every side of the story.
- Hugging Face Daily PapersBeyond Answering: Learning to Speak First and Act in Streaming Video
AURA 2.0 is a streaming video large language model that can proactively initiate conversations, call tools, and achieve interactive visual localization, with long-term memory capabilities. Its core upgrades include proactive model conversation (MIC), streaming-aware tool calling (SATC), and interactive visual grounding (IVG), which enhance streaming interaction through a three-stage training program. In public streaming benchmark tests, AURA 2.0 leads among open-source models, with its new interactive capabilities evaluated and validated.
Heat over time
- Now
- 6
- Peak
- 818 Nov, 18:00
- 24h change
- –
Hover or tap the chart to see each hour; use the arrow keys on a keyboard.