Machine Learning Street Talk (MLST)

A podcast by Machine Learning Street Talk (MLST)

Categories:

217 Episodes

  1. Prof. Randall Balestriero - LLMs without pretraining and SSL

    Published: 23/04/2025
  2. How Machines Learn to Ignore the Noise (Kevin Ellis + Zenna Tavares)

    Published: 8/04/2025
  3. Eiso Kant (CTO poolside) - Superhuman Coding Is Coming!

    Published: 2/04/2025
  4. The Compendium - Connor Leahy and Gabriel Alfour

    Published: 30/03/2025
  5. ARC Prize v2 Launch! (Francois Chollet and Mike Knoop)

    Published: 24/03/2025
  6. Test-Time Adaptation: the key to reasoning with DL (Mohamed Osman)

    Published: 22/03/2025
  7. GSMSymbolic paper - Iman Mirzadeh (Apple)

    Published: 19/03/2025
  8. Reasoning, Robustness, and Human Feedback in AI - Max Bartolo (Cohere)

    Published: 18/03/2025
  9. Tau Language: The Software Synthesis Future (sponsored)

    Published: 12/03/2025
  10. John Palazza - Vice President of Global Sales @ CentML ( sponsored)

    Published: 10/03/2025
  11. Transformers Need Glasses! - Federico Barbero

    Published: 8/03/2025
  12. Sakana AI - Chris Lu, Robert Tjarko Lange, Cong Lu

    Published: 1/03/2025
  13. Clement Bonnet - Can Latent Program Networks Solve Abstract Reasoning?

    Published: 19/02/2025
  14. Prof. Jakob Foerster - ImageNet Moment for Reinforcement Learning?

    Published: 18/02/2025
  15. Daniel Franzen & Jan Disselhoff - ARC Prize 2024 winners

    Published: 12/02/2025
  16. Sepp Hochreiter - LSTM: The Comeback Story?

    Published: 12/02/2025
  17. Want to Understand Neural Networks? Think Elastic Origami! - Prof. Randall Balestriero

    Published: 8/02/2025
  18. Nicholas Carlini (Google DeepMind)

    Published: 25/01/2025
  19. Subbarao Kambhampati - Do o1 models search?

    Published: 23/01/2025
  20. How Do AI Models Actually Think? - Laura Ruis

    Published: 20/01/2025

1 / 11

Welcome! We engage in fascinating discussions with pre-eminent figures in the AI field. Our flagship show covers current affairs in AI, cognitive science, neuroscience and philosophy of mind with in-depth analysis. Our approach is unrivalled in terms of scope and rigour – we believe in intellectual diversity in AI, and we touch on all of the main ideas in the field with the hype surgically removed. MLST is run by Tim Scarfe, Ph.D (https://www.linkedin.com/in/ecsquizor/) and features regular appearances from MIT Doctor of Philosophy Keith Duggar (https://www.linkedin.com/in/dr-keith-duggar/).

Visit the podcast's native language site