Why the Next AI Breakthrough May Come from Physics

What you'll learn

CuspAI uses generative AI to design entirely new molecules for carbon capture, later expanding into semiconductors, perovskites and battery materials.
Machine learning force fields compute forces on atoms three to four orders of magnitude faster than quantum mechanical approximations such as DFT.
Welling's book argues that the mathematics of diffusion models is equivalent to that of non-equilibrium thermodynamics, with cross-fertilization running both ways.
Neural networks that use waves, as the brain does, naturally reach the optimal edge-of-chaos regime through spontaneous symmetry breaking.

Frequently asked questions

What does CuspAI actually do?

CuspAI uses generative AI to design new materials for applications such as carbon capture with metal-organic frameworks, having expanded into semiconductors, perovskites for solar panels, removing PFAS and battery materials.

How does AI accelerate materials research?

Neural networks predict the forces on atoms normally computed with expensive quantum mechanical approximations such as density functional theory, three to four orders of magnitude faster, making molecular dynamics much cheaper.

Why is physics relevant to the next generation of AI?

According to Max Welling, the mathematics of generative AI, such as diffusion models, is equivalent to that of non-equilibrium thermodynamics. His group also uses waves and spontaneous symmetry breaking in neural networks so information travels deep through the network without fine-tuning the system.

Topics

ai-for-science materials-discovery physics-inspired-ai foundation-models frontier-research

In this video

CuspAI

Max Welling

Sources

What is known about this topic outside the broadcast, and where it says so.

Description from the channel

The conventional wisdom in AI is that the next breakthrough will come from more compute, more data, and larger models. But what if the next leap comes from somewhere else? In this episode, Max Welling—co-founder and CTO of CuspAI and professor at the University of Amsterdam—argues that physics may provide some of the ideas behind the next generation of AI systems. We begin with CuspAI’s work using generative AI to design entirely new materials for semiconductors, batteries, carbon capture, and clean energy. Max explains how foundation models for chemistry, agentic workflows, simulation, and automated experimentation are dramatically accelerating the search for new materials and reshaping scientific discovery. The conversation then broadens into a deeper question. Beyond giving AI new scientific problems to solve, can physics also teach us how to build better AI? Max explores surprising connections between machine learning and thermodynamics, why waves may become a new computational primitive for neural networks, and how concepts like symmetry breaking and statistical physics could inspire AI architectures beyond today’s scaling paradigm. Full show notes including references: https://twimlai.com/go/774. 🔔 Subscribe to our channel for more great content just like this: https://youtube.com/twimlai?sub_confirmation=1 📖 CHAPTERS =============================== 00:00 - Introduction 02:08 - From Equivariant Networks to AI for Science 04:55 - Founding CuspAI 07:30 - Using AI to Discover New Materials 09:03 - Designing Materials for Carbon Capture 13:20 - Partnerships and the CuspAI Business Model 14:59 - The End-to-End Materials Discovery Process 19:13 - Experiments and Self-Driving Labs 23:04 - Open-Source Molecular Dynamics on GPUs 25:23 - Foundation Models for Chemistry 30:20 - The Future of AI-Driven Materials Science 32:22 - Connecting Generative AI and Thermodynamics 39:29 - How Physics and Machine Learning Can Inform Each Other 44:53 - Waves as a New Primitive for Neural Networks 49:34 - Memory, Stability, and the Edge of Chaos 52:40 - Spontaneous Symmetry Breaking in Neural Networks 56:10 - The Two-Way Exchange Between AI and Physics 🗣️ CONNECT WITH US! =============================== Subscribe to the TWIML AI Podcast: https://twimlai.com/podcast/twimlai/ Follow us on Twitter: https://twitter.com/twimlai Follow us on LinkedIn: https://www.linkedin.com/company/twimlai/ Join our Slack Community: https://twimlai.com/community/ Subscribe to our newsletter: https://twimlai.com/newsletter/ Want to get in touch? Send us a message: https://twimlai.com/contact/