الباحثون

Junhao Xu

المنشورات 2

نسخة أولية وصول مفتوح

Qwen-Audio-3.1-Realtime: Towards Reliable Agentic Voice Interaction

Lujia Bao, Qian Chen, Luyao Cheng وآخرون · 2026

Real-time voice assistants must reason over evolving requests, execute actions, and follow conversational rules. Qwen-Audio-3.1-Realtime brings these requirements together through Think, Act, and Speak and Coordinate. Think combines Core-Cocktail supervised fine-tuning with Multimodality and Multi-Teacher On-Policy Dis …

نسخة أولية وصول مفتوح

Text Scores Do Not Establish Performance on Lexically Non-Diagnostic Speech Tasks: A Qwen2-Audio Quantization Case Study

Text-output scores alone do not show whether quantization preserves performance on speech tasks whose target labels cannot be recovered from the transcript. We evaluate fixed mixed 4/8-bit Qwen2-Audio-7B-Instruct allocations averaging 6 and 7 bits per parameter on 508 English-to-German FLEURS utterances and on 512 RAVD …

المؤلفون المشاركون