a16z Podcast
The Frontier of Spatial Intelligence with Fei-Fei Li
a16z Podcast
•November 13, 2025•44 min
0
a16z Podcast•Nov 13, 2025
Why It Matters
Marble lowers the technical barrier to 3‑D creation, accelerating adoption of spatial AI across industries and opening new revenue streams for content platforms.
Key Takeaways
- •Marble generates 3D scenes from text prompts
- •World Labs builds Large World Models for spatial AI
- •Spatial intelligence expands beyond language models to 3D interaction
- •Early AI breakthroughs like ImageNet underpin today’s generative 3D tools
- •Industry applications include VR, AR, and physical world simulations
Pulse Analysis
Fei‑Fei Li and Justin Johnson have been architects of modern computer vision since the ImageNet era, laying the groundwork for today’s multimodal breakthroughs. Their conversation with a16z partner Martin Casado traces the shift from early deep‑learning winters to the current surge in generative AI, emphasizing how large‑scale visual datasets and compute advances unlocked spatial reasoning. By extending the principles that powered 2‑D image classification into three dimensions, they introduced the concept of Large World Models—systems that can perceive, generate, and act within a virtual environment.
Marble, World Labs’ first commercial offering, translates text or image prompts into fully realized 3‑D scenes with a single click. The platform abstracts complex pipelines—mesh generation, texture mapping, and physics simulation—into an intuitive interface, enabling independent creators, game studios, and enterprise designers to prototype immersive environments at unprecedented speed. By leveraging pretrained Large World Models, Marble delivers consistent geometry and realistic lighting without requiring specialized 3‑D expertise, positioning it as a disruptive alternative to traditional CAD and manual modeling tools.
The emergence of spatial intelligence signals a new frontier for both consumer and enterprise markets. Companies can now embed dynamic 3‑D content into e‑commerce, training simulations, and digital twins, reducing development cycles and unlocking richer user experiences. Investors are watching closely as Large World Models promise scalability comparable to language models, suggesting a wave of startups focused on generative 3‑D capabilities. As hardware accelerators improve and data pipelines mature, the barrier between imagination and virtual realization will continue to shrink, making spatial AI a core pillar of future digital ecosystems.
Episode Description
Fei-Fei Li and Justin Johnson are pioneers in AI. While the world has only recently witnessed a surge in consumer AI, they have long been laying the groundwork for the innovations transforming industries today.
With the recent launch of Marble, the first product from their company World Labs, we are revisiting this conversation to explore the ideas that started it all. World Labs is focused on spatial intelligence, building Large World Models that can perceive, generate, and interact with the 3D world. Marble brings that vision to life, allowing anyone, from individual creators to major platforms, to generate 3D scenes directly from text or image prompts and turn complex 3D creation into a simple, creative process.
In this episode, a16z general partner Martin Casado talks with Fei-Fei and Justin about the journey from early AI winters to the rise of deep learning and multimodal AI. From foundational breakthroughs like ImageNet to the cutting-edge realm of spatial intelligence, they discuss the evolution of the field and what is next for innovation at World Labs.
Timecode:
0:00 – The Next Decade of AI
2:45 – Origins: Backgrounds of the Founders
6:50 – The Rise of Deep Learning & ImageNet
8:00 – Algorithmic Unlocks: Compute, Data, and Supervised Learning
12:00 – From Predictive to Generative AI
16:20 – The Journey to Spatial Intelligence
18:35 – Defining Spatial Intelligence
21:15 – 3D Data, Computer Vision, and Breakthroughs
23:15 – Reconstruction vs. Generation in Computer Vision
24:45 – Spatial Intelligence vs. Language Models
29:00 – Applications: Virtual, Augmented, and Physical Worlds
39:55 – Building World Labs: Team and Vision
41:55 – The North Star: Measuring Success in Spatial Intelligence
Resources:
Learn more about World Labs: https://www.worldlabs.ai
Learn more about Marble: https://Marble.WorldLabs.ai
Find Fei-Fei on Twitter: https://x.com/drfeifei
Find Justin on Twitter: https://x.com/jcjohnss
Find Martin on Twitter: https://x.com/martin_casado
Stay Updated:
If you enjoyed this episode, be sure to like, subscribe, and share with your friends!
Find a16z on X: https://x.com/a16z
Find a16z on LinkedIn: https://www.linkedin.com/company/a16z
Listen to the a16z Podcast on Spotify: https://open.spotify.com/show/5bC65RDvs3oxnLyqqvkUYX
Listen to the a16z Podcast on Apple Podcasts: https://podcasts.apple.com/us/podcast/a16z-podcast/id842818711
Follow our host: https://x.com/eriktorenberg
Please note that the content here is for informational purposes only; should NOT be taken as legal, business, tax, or investment advice or be used to evaluate any investment or security; and is not directed at any investors or potential investors in any a16z fund. a16z and its affiliates may maintain investments in the companies discussed. For more details please see a16z.com/disclosures.
Stay Updated:
Find a16z on X
Find a16z on LinkedIn
Listen to the a16z Podcast on Spotify
Listen to the a16z Podcast on Apple Podcasts
Follow our host: https://twitter.com/eriktorenberg
Please note that the content here is for informational purposes only; should NOT be taken as legal, business, tax, or investment advice or be used to evaluate any investment or security; and is not directed at any investors or potential investors in any a16z fund. a16z and its affiliates may maintain investments in the companies discussed. For more details please see a16z.com/disclosures.
Hosted by Simplecast, an AdsWizz company. See pcm.adswizz.com for information about our collection and use of personal data for advertising.
Show Notes
0
Comments
Want to join the conversation?
Loading comments...