Do AI Systems Have World Models? Probing Reasoning, Forecasting, and Generalization
Shiry Ginosar (Toyota Technological Institute at Chicago) https://simons.berkeley.edu/talks/shi... Topics in Intelligence: World Models and Social Reasoning Recent advances in vision and vision-language models have renewed interest in a fundamental question: do these systems acquire internal models of the world? Although such models are trained on images, videos, and other human-produced representations rather than direct experience, they often exhibit behaviors suggestive of knowledge about objects, spaces, and dynamics. Determining what these behaviors reveal about underlying world models, however, remains challenging. In this talk, I will discuss how Kenneth Craik's conception of mental models can provide a useful lens for thinking about this question. Craik argued that internal models enable organisms to reason about alternatives, anticipate future events, and apply past experience to new situations. Building on this perspective, I will examine two recent lines of work that probe these capabilities in modern AI systems: spatial reasoning in language models and motion forecasting in visual models. Together, these examples illustrate both the promise and the limitations of current approaches to studying world models in artificial systems.

Talk by Phillip Isola

Natural behavior is learned through dopamine-mediated reinforcement

World Models and the Emergence of a “First-Person” Perspective in an AI

Storchennest Live Webcam in Bad Salzungen, Thüringen

Turing Award Winner: Disagreeing with Google, Postgres, Future Problems | Mike Stonebraker

Inside Anthropic, the $965 Billion AI Juggernaut | The Circuit

Embodied cognitive evolution

WHY GRAVITY PROVES THERE ARE NO ADVANCED CIVILIZATIONS WATCHING US | LEONARD SUSSKIND EXPLAINS

Inference, Diffusion, World Models, and More | YC Paper Club

Bridging the gap between Minds & Machines

Ukraine's drone war is isolating Crimea

Creator of C++: Bell Labs, Negative Overhead Abstraction, Mistakes | Bjarne Stroustrup

Social NeuroAI of World Modeling: Embodied Dynamics, Collective Intelligence and Relational...

Yann LeCun Says LLMs Have 2 Years Left…

Sarah Paine - Why Putin and Xi can't escape geography

Yann LeCun: World Models: Enabling the next AI revolution

Interpretability: Understanding how AI models think

Reinventing Entropy | Compression is Intelligence Part 1

Demis Hassabis: Why AGI is Bigger than the Industrial Revolution & Where Are The Bottlenecks in AI

