看影片時,畫面、對話和背景聲音常要分開處理,WeChat Vision 推出的 WeMM-Video 能把它們放在一起理解,也能用中文或英文回答。
- 這個開放權重模型家族有 2B、4B、9B 和 35B-A3B 等尺寸,可接收文字、圖片、音訊和影片,並提供直接回答與深入推理兩種模式。技術報告稱,35B-A3B 在同等規模的開放模型中影音表現突出。
- Thinking 模式在 17 項一般影音基準中的 16 項,勝過 Seed2.0-Mini-0428 和 Qwen3.5-Omni-Flash。
AI 伴隨問答
針對這篇報導有疑問?可直接點選快捷問題或向 AI 追問背景脈絡與技術細節:
WeMM-Video 把影片畫面、對話與環境聲音放在同一條時間線理解,報告也比較了不同規模模型在多項影音基準上的表現。
WeChat Vision at Tencent releases WeMM-Video, an open-weight model family for joint audio-visual understanding and reasoning. Available in 2B, 4B, 9B, and 35B-A3B sizes, it accepts text, images, audio, and video and responds in Chinese or English. 📜 Apache 2.0.
🤖 https://t.co/cIqyr6AkNy
📄 Technical report https://t.co/pWyQK0fR7M
🎬 Understand the picture and the soundtrack together. Timestamped frames and audio tokens share a timeline, connecting actions, dialogue, and ambient sounds.
🏆 Strong audio-visual results. The paper reports SOTA among comparably sized open models for 35B-A3B. Its Thinking mode beats Seed2.0-Mini-0428 and Qwen3.5-Omni-Flash on 16 of 17 general audio-visual benchmarks each.
🪶 Competitive at smaller sizes. The 9B Thinking model outperforms Qwen3-Omni-30B-A3B-Instruct and MiniCPM-o-4.5-9B across most general audio-visual benchmarks in the paper.
🧠 Direct answers or deeper reasoning. Switch between Instruct and Thinking modes across the family.
🛠️ Choose your deployment format. BF16, FP8, AWQ, GGUF, and NVFP4 checkpoints, with Transformers support and patched vLLM/SGLang serving.