Best AI papers explained

526 Episoade

1. From RL Distillation to Autonomous LLM Agents

   Publicat: 29.05.2025
2. Prompting, Auto-Prompting, and Human-AI Communication

   Publicat: 29.05.2025
3. Textual Gradients for LLM Optimization

   Publicat: 29.05.2025
4. Large Language Models as Markov Chains

   Publicat: 28.05.2025
5. Metastable Dynamics of Chain-of-Thought Reasoning: Provable Benefits of Search, RL and Distillation

   Publicat: 28.05.2025
6. Selective induction heads: how transformers select causal structures in context

   Publicat: 28.05.2025
7. The Evolution of Statistical Induction Heads: In-Context Learning Markov Chains

   Publicat: 28.05.2025
8. How Transformers Learn Causal Structure with Gradient Descent

   Publicat: 28.05.2025
9. Planning anything with rigor: general-purpose zero-shot planning with llm-based formalized programming

   Publicat: 28.05.2025
10. Automated Design of Agentic Systems

    Publicat: 28.05.2025
11. What’s the Magic Word? A Control Theory of LLM Prompting

    Publicat: 28.05.2025
12. BoNBoN Alignment for Large Language Models and the Sweetness of Best-of-n Sampling

    Publicat: 27.05.2025
13. RL with KL penalties is better viewed as Bayesian inference

    Publicat: 27.05.2025
14. Asymptotics of Language Model Alignment

    Publicat: 27.05.2025
15. Qwen 2.5, RL, and Random Rewards

    Publicat: 27.05.2025
16. Theoretical guarantees on the best-of-n alignment policy

    Publicat: 27.05.2025
17. Score Matching Enables Causal Discovery of Nonlinear Additive Noise Models

    Publicat: 27.05.2025
18. Improved Techniques for Training Score-Based Generative Models

    Publicat: 27.05.2025
19. Your Pre-trained LLM is Secretly an Unsupervised Confidence Calibrator

    Publicat: 27.05.2025
20. AlphaEvolve: A coding agent for scientific and algorithmic discovery

    Publicat: 27.05.2025