CEOInterviews.AI
Start App
Try: AI strategy tariffs earnings guidance layoffs interest rates growth

Justin Johnson

Co-founder, World Labs

Search every verified Justin Johnson interview, podcast appearance, and on-the-record quote — each transcript cross-checked by AI and human review to confirm speaker identity. Justin Johnson, co-founder of World Labs, discussed the company's recently announced Atlas model in several September 2026 interviews. He described Atlas as a multimodal world model that performs "new view prediction," generating image and video frames from given views of a scene with pixel-perfect camera control and 3D reconstruction. Johnson contrasted this with next-token prediction in language models and next-frame prediction in video models, stating that new view prediction is a fundamental primitive for spatial intelligence. He also discussed the potential applications of world models across entertainment, virtual reality, construction, and robotics, and mentioned the company's Marble system as a product users can try. Johnson spoke about the broader shift toward world models, saying many researchers believe language models are not sufficient for capabilities like understanding, generating, simulating, and reconstructing worlds. He noted that there is no established recipe for building these systems and that the field is still at an early stage, with training compute being a primary bottleneck. In discussions about robotics, he described approaches such as in-context learning and real-to-sim-to-real pipelines, where simulations matching the final use case can be used to fine-tune or evaluate robotics foundation models.

Recent appearances

  • World Models Will Eclipse LLMs | World Labs Co-Founder

    Justin Johnson joins MTS to discuss Atlas, World Labs' multimodal world model that generates image and video frames with pixel-perfect camera control. Johnson explains how world models can be used for generation, reconstruction, and simulation across entertainment, robotics, and VR applications. Check out our sponsor Lovable: ⁠https://lovable.dev.⁠ Turn ideas into software people love. -- ⁠https://x.com/jcjohnss⁠ -- MTS is a live news and interview show covering technology, business, politics, and culture as it happens. Follow MTS:  X |⁠ ⁠⁠⁠  / mtslive⁠⁠   YouTube |⁠ ⁠⁠⁠   / @mtsituation   Sp…

    Watch on YouTube ↗

  • Why Fei-Fei Li Is Betting on Spatial Intelligence

    World Labs co-founders Fei-Fei Li, Justin Johnson, and Ben Mildenhall join a16z General Partner Martin Casado to discuss Atlas, their latest world model, and what it reveals about the pursuit of spatial intelligence. At the center of Atlas is what the team calls “new view prediction”: given images or views of a scene, the model predicts what that environment should look like from a different position in space and time. This brings generation and 3D reconstruction into the same model, and raises a broader question about whether predicting views could become a useful primitive for understanding…

    Watch on YouTube ↗

  • Are World Models What Comes After Language Models?

    In this episode, Justin Johnson, co-founder of World Labs, joins us to discuss world models and the emerging field of spatial AI. We explore why many researchers see capabilities beyond language as an important frontier for AI, and what it means to build models that can understand, generate, and simulate the environments around them. Justin explains the different approaches to world modeling, including explicit 3D representations and generative models, and why there is still no established recipe for building these systems. We also discuss World Labs’ Marble system, which can generate naviga…

    Watch on YouTube ↗

  • After LLMs: Spatial Intelligence and World Models — Fei-Fei Li & Justin Johnson, World Labs

    Fei-Fei Li and Justin Johnson are cofounders of World Labs, who have recently launched Marble (https://marble.worldlabs.ai/), a new kind of generative “world model” that can create editable 3D environments from text, images, and other spatial inputs. Marble lets creators generate persistent 3D worlds, precisely control cameras, and interactively edit scenes, making it a powerful tool for games, film, VR, robotics simulation, and more. In this episode, Fei-Fei and Justin share how their journey from ImageNet and Stanford research led to World Labs, why spatial intelligence is the next frontier…

    Watch on YouTube ↗

  • “The Future of AI is Here” — Fei-Fei Li Unveils the Next Frontier of AI

    Fei-Fei Li and Justin Johnson are pioneers in AI. While the world has only recently witnessed a surge in consumer AI, our guests have long been laying the groundwork for innovations that are transforming industries today. In this episode, a16z General Partner Martin Casado joins Fei-Fei and Justin to explore the journey from early AI winters to the rise of deep learning and the rapid expansion of multimodal AI. From foundational advancements like ImageNet to the cutting-edge realm of spatial intelligence, Fei-Fei and Justin share the breakthroughs that have shaped the AI landscape and reveal…

    Watch on YouTube ↗

  • Justin Johnson - Invited Talk at the VQA Workshop 2021

    Invited Talk by Justin Johnson on "Learning Visual Representations from Language" at the Visual Question Answering Workshop, CVPR 2021.

    Watch on YouTube ↗

  • From Recognition to Reasoning | Justin Johnson

    Justin Johnson is currently Assistant Professor at University of Michigan, in the Computer Science and Engineering (CSE) Division. This AI Seminar was hosted by Michigan AI on November 19, 2019.

    Watch on YouTube ↗

  • From Recognition to Reasoning | Justin Johnson

    Prof. Justin Johnson, Michigan AI (Computer Science & Engineering, University of Michigan) talks at the Michigan AI Symposium 2019.

    Watch on YouTube ↗

Other executives at World Labs

The summary and quote tags on this profile are produced with AI assistance from verified, first-person interview transcripts, then checked by our team to confirm the speaker's identity and the accuracy of every quote. See how we verify →