The converse is also worth asking — whether simulating artificial environments (for instance a 3d representation of a Youtube video) might have unintended negative consequences. Fei-Fei Li’s startup World Labs, which aims to make the leading “world model” — an alternative to language models based on tokenizing physical space rather than words — recently raised a substantial amount of money. As consumer-facing robots become more plausible, the business case for such a model is obvious. But what physical spaces are “world” models actually being trained on? The contemporary physical environment, sound-proofed, plastic-coated, and artificially-colored, is radically different from the environment that Homo sapiens evolved to excel in.
Nature, Published online: 25 February 2026; doi:10.1038/d41586-026-00578-w，详情可参考Line官方版本下载
СюжетВстреча Путина и Зеленского。业内人士推荐爱思助手下载最新版本作为进阶阅读
Subscribe to get our editors’ pick of the Guardian’s award-winning sport coverage. We’ll email you the stand-out features and interviews, insightful analysis and highlights from the archive, plus films, podcasts, galleries and more – all arriving in your inbox at every Friday lunchtime. And we’ll set you up for the weekend and let you know our live coverage plans so you’ll be ahead of the game. Here’s what you can expect from us.
创作者或许可以直接在3D空间中布置虚拟摄像机，规划其运动轨迹，而AI则负责实时渲染出该视角下的视频流。Seedance 2.0的“导演模式”可以看作是这一方向的早期雏形。