Google DeepMind、ワールドモデル「Genie 4」発表 音声や会話もリアルタイム生成、Geminiと連携
ITmedia AI+ja
Google DeepMindは、対話型の仮想世界をリアルタイム生成するAI「Genie 4」を発表した。映像品質や物理演算が向上し、環境音や会話音声の同時生成に対応。人物の自然な動作やテキストによる環境操作が可能となった。まずは研究プレビューとして提供し、順次「Google AI Ultra」加入者等へ展開する。
This is a short summary published by AI Global Wire. The full article is owned and hosted by ITmedia AI+ — open it there to read it in full.
Read the full story at ITmedia AI+Related AI news
- Walmart says AI training is boosting confidence with the technology among its 2.1 million associatesCNBC Technology · October 27, 2026
- Google Deepmind's Genie 4 puts a modern spin on agent designs that predate LLMsThe Decoder · October 27, 2026
- Google’s Genie 4 world model adds audio, more realistic worlds, and real-time steeringTechCrunch AI · October 27, 2026
- Oracle adds ChatGPT and Codex to its app stack and expands Oracle Cloud Infrastructure lineup with Google TPUs, OpenAI's Jalapeño chip, and Cerebras hardware (Seema Mody/CNBC)Techmeme · October 27, 2026
- Google launches Genie 4, a world model powered by Gemini 3.8 Flash designed to generate interactive AI simulations, initially as a preview to trusted testers (Jay Peters/The Verge)Techmeme · October 27, 2026
- DeepMind unveils Genie 4 world model promising more realistic physics and humansArs Technica AI · October 27, 2026