Spatial Intelligence Is AI’s Next Frontier

注解

institute n.（名词） /ˈɪnstɪtuːt/（美）：研究所；学院；机构

arithmetic n. /əˈrɪθmətɪk/ 算术；四则运算

reverberates v. /rɪˈvɝːbəreɪts/（美）回响；反射回声，引申义：持续产生影响；余波不断

be little more than 无非是；不过是；充其量只是

remarkable adj.非凡的；卓越的；引人注目的

relentless adj. /rɪˈlentləs/ 不懈的；持续不断的；毫不松懈的

quest n./kwest/追求；探索；长期而执着的寻找

Yet：转折（“然而”）

wordsmiths n. 构词：word（词） + smith（匠人） 含义：文字工匠；擅长玩弄语言的人
语感：强调“语言技巧高” 不等于“真正理解世界”，在这里不是褒义，而是带克制的讽刺。

eloquent /ˈeləkwənt/ adj. 雄辩的；有说服力的；表达流畅而优雅的（尤指语言、写作或演讲）

ungrounded /ʌnˈɡraʊndɪd/ adj. 不接地气的；缺乏现实基础的；未被事实或经验支撑的

scaffolding /ˈskæfəʊldɪŋ/ n. 脚手架；支撑结构；（比喻）认知或学习的支架 ← 派生自：scaffold /ˈskæfəʊld/ n. 脚手架；支架

cognition /kɒɡˈnɪʃən/ n. 认知；认识过程 ← 派生自：cognize /ˈkɒɡnaɪz/ v. 认识；感知

正文

Li is co-director of Stanford’s Human-Centered AI Institute and co-founder CEO of World Labs

李是斯坦福大学“以人为中心人工智能研究院”（Human-Centered AI Institute，简称 HAI）的联合主任，同时也是 World Labs 的联合创始人兼首席执行官。

In 1950, when computing was little more than automated arithmetic and simple logic, Alan Turing asked a question that still reverberates today: can machines think? It took remarkable imagination to see what he saw, which is that intelligence might someday be built rather than born. That insight later launched a relentless scientific quest called artificial intelligence. Twenty-five years into my own career in AI, I still find myself inspired by Turing’s vision. But how close are we? The answer isn’t simple.

1950 年，当计算机还只是自动化算术和简单逻辑的延伸时，艾伦·图灵提出了一个至今仍在回响的问题：机器能思考吗？要洞察到他所看到的未来，需要非凡的想象力——那就是，智能或许有一天可以被“构建”出来，而非只能“天生”具备。
这一洞见后来引发了一场持续至今、势不可挡的科学探索，人们称之为人工智能在我从事人工智能研究的第 25 个年头，我依然不断被图灵的远见所激励。
但我们究竟离那个目标还有多远？答案并不简单。

Today, leading AI technology such as large language models (LLMs) have begun to transform how we access and work with abstract knowledge. Yet they remain wordsmiths in the dark, eloquent but inexperienced, knowledgeable but ungrounded.

如今，以大语言模型为代表的前沿 AI 技术，已经开始改变我们获取和处理抽象知识的方式。然而，它们依然像是黑暗中的“文字匠人”——表达流畅却缺乏真实经验，信息丰富却没有牢固的现实根基。

For humans, spatial intelligence is the scaffolding upon which our cognition is built. It’s at work when we passively observe or actively seek to create. It drives our reasoning and planning, even on the most abstract topics. And it’s essential to the way we interact—verbally or physically, with our peers or with the environment itself. When machines are endowed with this ability, it will transform how we create and interact with real and virtual worlds—revolutionizing storytelling, robotics, scientific discovery, and beyond. This is AI’s next frontier, and why 2025 was such a pivotal year.

The candid truth is that AI’s spatial capabilities remain far from the human level. But tremendous progress has indeed been made. Multimodal LLMs, trained with voluminous multimedia data in addition to textual data, have introduced some basics of spatial awareness, and today’s AI can analyze pictures, answer questions about them, and generate hyperrealistic images and short videos.

But there is much more to be done. Building spatially intelligent AI requires something even more ambitious than LLMs: world models, new types of generative models whose capabilities of understanding, reasoning, generation and interaction with the semantically, physically, geometrically and dynamically complex worlds - virtual or real - are far beyond the reach of today’s LLMs.

This technology is still nascent, yet exciting progress is underway. The applications of spatial intelligence span varying timelines. Creative tools are emerging now—World Labs’ Marble already puts these capabilities in creators’ and storytellers’ hands. Robotics represents an ambitious mid-term horizon as we refine the loop between perception and action. The most transformative scientific applications will take longer but promise a profound impact on human flourishing.

For the first time in history, we’re poised to build machines that we can rely on as true partners in the greatest challenges we face—whether accelerating how we understand diseases in the lab or supporting us in our most vulnerable moments of sickness, injury, or age. We’re on the cusp of technology that elevates the aspects of life we care about most. This is a vision of deeper, richer, more empowered lives. Almost a half billion years after nature unleashed the first glimmers of spatial intelligence in ancestral animals, we’re lucky enough to find ourselves among the generation of technologists who we may soon endow machines with the same capability—and privileged enough to harness those capabilities for the benefits of people everywhere.

Adapted from Li’s essay “From Words to Worlds: Spatial Intelligence is AI’s Next Frontier.”