550 Episoder

  1. Self-Boost via Optimal Retraining: An Analysis via Approximate Message Passing

    Publisert: 27.11.2025
  2. Prompted Policy Search: Reinforcement Learning through Linguistic and Numerical Reasoning in LLMs

    Publisert: 27.11.2025
  3. Ilya Sutskever – We're moving from the age of scaling to the age of research

    Publisert: 26.11.2025
  4. Cognitive Foundations for Reasoning and Their Manifestation in LLMs

    Publisert: 26.11.2025
  5. Natural emergent misalignment from reward hacking in production RL

    Publisert: 25.11.2025
  6. Evolution Strategies at the Hyperscale

    Publisert: 25.11.2025
  7. The Path Not Taken: RLVR Provably Learns Off the Principals

    Publisert: 23.11.2025
  8. Back to Basics: Let Denoising Generative Models Denoise

    Publisert: 23.11.2025
  9. LLM Prompt Duel Optimizer: Efficient Label-Free Prompt Optimization

    Publisert: 22.11.2025
  10. Black-Box On-Policy Distillation of Large Language Models

    Publisert: 20.11.2025
  11. Solving a million step LLM task with zero errors

    Publisert: 20.11.2025
  12. Not All Thoughts Matter: Selective Attention for Efficient Reasoning

    Publisert: 19.11.2025
  13. Sample-Efficient Parametric Learning from Natural Language

    Publisert: 19.11.2025
  14. Bayesian Optimization in Language space: An Eval-Efficient AI Self-Improvement Framework

    Publisert: 18.11.2025
  15. Context Engineering: Sessions, Memory

    Publisert: 16.11.2025
  16. The Era of Agentic Organization: Learning to Organize with Language Models

    Publisert: 15.11.2025
  17. Understanding neural networks through sparse circuits

    Publisert: 14.11.2025
  18. Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning

    Publisert: 14.11.2025
  19. Multi-Agent Evolve: LLM Self-Improvement Through Co-Evolution

    Publisert: 14.11.2025
  20. LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics

    Publisert: 14.11.2025

1 / 28

Cut through the noise. We curate and break down the most important AI papers so you don’t have to.

Visit the podcast's native language site