506 Episodo

  1. From RL Distillation to Autonomous LLM Agents

    Publicado: 29/5/2025
  2. Prompting, Auto-Prompting, and Human-AI Communication

    Publicado: 29/5/2025
  3. Textual Gradients for LLM Optimization

    Publicado: 29/5/2025
  4. Large Language Models as Markov Chains

    Publicado: 28/5/2025
  5. Metastable Dynamics of Chain-of-Thought Reasoning: Provable Benefits of Search, RL and Distillation

    Publicado: 28/5/2025
  6. Selective induction heads: how transformers select causal structures in context

    Publicado: 28/5/2025
  7. The Evolution of Statistical Induction Heads: In-Context Learning Markov Chains

    Publicado: 28/5/2025
  8. How Transformers Learn Causal Structure with Gradient Descent

    Publicado: 28/5/2025
  9. Planning anything with rigor: general-purpose zero-shot planning with llm-based formalized programming

    Publicado: 28/5/2025
  10. Automated Design of Agentic Systems

    Publicado: 28/5/2025
  11. What’s the Magic Word? A Control Theory of LLM Prompting

    Publicado: 28/5/2025
  12. BoNBoN Alignment for Large Language Models and the Sweetness of Best-of-n Sampling

    Publicado: 27/5/2025
  13. RL with KL penalties is better viewed as Bayesian inference

    Publicado: 27/5/2025
  14. Asymptotics of Language Model Alignment

    Publicado: 27/5/2025
  15. Qwen 2.5, RL, and Random Rewards

    Publicado: 27/5/2025
  16. Theoretical guarantees on the best-of-n alignment policy

    Publicado: 27/5/2025
  17. Score Matching Enables Causal Discovery of Nonlinear Additive Noise Models

    Publicado: 27/5/2025
  18. Improved Techniques for Training Score-Based Generative Models

    Publicado: 27/5/2025
  19. Your Pre-trained LLM is Secretly an Unsupervised Confidence Calibrator

    Publicado: 27/5/2025
  20. AlphaEvolve: A coding agent for scientific and algorithmic discovery

    Publicado: 27/5/2025

12 / 26

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