AI 终于能像真人一样边听边看边回应
现在的 AI 对话要么只能听声音、要么只能看文字，而且得等你把话说完才回应。这篇直接把「看画面、听声音、说人话」塞进一个模型里，不用拼凑语音识别、语言模型、视频生成等一堆模块。它用「因果注意力」让模型像人一样边接收边输出——你刚开口它就能开始反应，画面和声音同步，延迟约 200 毫秒。这不是你明天能用上的产品，但它指明了下一代交互 AI 的方向：不再分段处理，而是像真人一样实时感知、思考、回应。
📄 原文摘要(英文)
We present Wan-Streamer, a native-streaming, end-to-end interactive foundation model designed from the ground up for real-time, low-latency, full-duplex audio-visual interaction. Wan-Streamer seamlessly models language, audio, and video as both input and output within a single Transformer, where the sequence is represented as interleaved visual, audio, and text input tokens together with visual, audio, and text output tokens, coordinated by block-causal attention for incremental streaming. Unlike cascaded interactive systems that rely on separate VAD, ASR, language, TTS, audio-driven animation, or video-generation modules, Wan-Streamer does not rely on external language, speech, avatar, or video-generation modules: perception, reasoning, generation, response timing, turn management, and cross-modal synchronization are learned jointly within one unified model, reducing pipeline latency and error accumulation. To support natural audio-visual responsiveness, we redesign the entire stack around streamability, including causal encoders, causal decoders, block-causal attention, and low-latency multimodal token scheduling, enabling streaming units as short as 160 ms at 25 fps. Wan-Streamer achieves approximately 200 ms model-side response latency and approximately 550 ms total interaction latency when combined with 350 ms bidirectional network latency, supporting sub-second duplex audio-visual communication. These results position Wan-Streamer as a unified, end-to-end, multimodal interactive foundation model for low-latency streaming interaction.