← Back to Model Beat
4Open Source·6d ago

Wan-Streamer v0.1: End-to-end Real-time Interactive Foundation Models

Researchers have introduced Wan-Streamer, an interactive foundation model designed to process audio, video, and text simultaneously in real time. By utilizing a native-streaming architecture, the system aims to reduce latency for full-duplex communication between users and AI agents.

Covered by 1 source

  • AarXiv CS.AILianghua Huang, Zhifan Wu, Wei Wang, Yupeng Shi, Mengyang Feng, Junjie He, Chenwei Xie, Yu Liu, Jingren Zhou, Ang Wang, Bang Zhang, Baole Ai, Chen Liang, Cheng Yu, Chongyang Zhong, Jinwei Qi, Kai Zhu, Pandeng Li, Peng Zhang, Wenyuan Zhang, Xinhua Cheng, Yitong Huang, Yun Zheng, Zoubin Bi6d ago

Related stories

Open SourceAnthropic Economic Index report: CadencesJun 26Open SourcePP-OCRv6 on Hugging Face: 50-Language OCR from 1.5M to 34.5M ParametersJun 22Open SourceOpen-source LLMs administer maximum electric shocks in a Milgram-like obedience experimentJun 24Open SourceGetty Images Soars 200% in Early Trading After OpenAI DealJun 22