484 Episodes

  1. Textual Gradients for LLM Optimization

    Published: 5/29/2025
  2. Large Language Models as Markov Chains

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

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

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

    Published: 5/28/2025
  6. How Transformers Learn Causal Structure with Gradient Descent

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

    Published: 5/28/2025
  8. Automated Design of Agentic Systems

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

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

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

    Published: 5/27/2025
  12. Asymptotics of Language Model Alignment

    Published: 5/27/2025
  13. Qwen 2.5, RL, and Random Rewards

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

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

    Published: 5/27/2025
  16. Improved Techniques for Training Score-Based Generative Models

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

    Published: 5/27/2025
  18. AlphaEvolve: A coding agent for scientific and algorithmic discovery

    Published: 5/27/2025
  19. Harnessing the Universal Geometry of Embeddings

    Published: 5/27/2025
  20. Goal Inference using Reward-Producing Programs in a Novel Physics Environment

    Published: 5/27/2025

11 / 25

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