Best AI papers explained

425 Episodes

1. Prompting, Auto-Prompting, and Human-AI Communication

   Published: 5/29/2025
2. Textual Gradients for LLM Optimization

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

    Published: 5/27/2025