AURA 2.0
Huawei Research's open streaming video LLM (built on Qwen3.5-9B) that, for the first time, initiates conversations itself when it spots something worth discussing in a live video stream — plus stream-aware tool calling and interactive visual grounding.
Why it matters
First streaming video model trained to start open-ended conversations without any user prompt (Model-Initiated Conversation), alongside tool use grounded in the live visual stream — the missing step toward genuinely proactive video assistants.
What you could build with it
A startup building live monitoring tools could point this model at a factory floor or retail camera feed and get spoken alerts only when something actually needs attention — a safety hazard, a stalled line, a customer waiting too long — instead of paying a human to watch the feed or spamming alerts on a fixed schedule.
Does it hold up?
Too early to judge — paper-only so far; the promised weights/code link has not surfaced yet, and all benchmark results are the authors' own on public streaming benchmarks.
Built with AURA 2.0
- AURA 2.0: Proactive AI for Real-Time Video Analysisorigin.saiwa.ai · Writeup of the paper covering MIC, stream-aware tool calling and visual grounding, and its leading scores among open-source streaming models.
Learn more
First spotted on article: source.
More AI models
Edge0-145B: open 145B MoE that runs on a single consumer GPUEdge0 open-sourced 145B and 120B latent-MoE models derived from Qwen3.8-Flash-Next, plus an inference framework that…models · JEV 0.74Strata: run a 125B model on a gaming PCFree, MIT-licensed local inference engine that runs Qwen3.8-Flash-Next (125B MoE, about 6B active per token) on…models · JEV 0.73Qwen4-Max: Alibaba's new flagship model goes liveAlibaba's 2.4T-parameter flagship is now generally available via API, with a 1M-token context, native vision, and…models · JEV 0.67smolmaxxing: run 16B LLMs on a 1 GB TV box or a 2013 iPadAn MIT-licensed llama.cpp patch set that runs language models up to a 16B MoE on devices with about 1 GB of usable RAM…models · JEV 0.65Blue TTS v3: a 388MB open text-to-speech model with voice cloningAn open-source 388MB text-to-speech model (MIT) with voice cloning from about 10 seconds of speech, 7 languages, 15…models · JEV 0.65Haru-4BOpen full-duplex spoken-dialogue foundation model that listens and speaks simultaneously (7.5 Hz frames, 133 ms per…models · JEV 0.63
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.