Best AI papers explained

456 Episodes

1. What’s the Magic Word? A Control Theory of LLM Prompting

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

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

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

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

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

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

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

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

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

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

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

    Published: 5/27/2025
13. Trial-Error-Explain In-Context Learning for Personalized Text Generation

    Published: 5/27/2025
14. Reinforcement Learning for Reasoning in Large Language Models with One Training Example

    Published: 5/27/2025
15. Test-Time Reinforcement Learning (TTRL)

    Published: 5/27/2025
16. Interpreting Emergent Planning in Model-Free Reinforcement Learning

    Published: 5/26/2025
17. Agentic Reward Modeling_Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems

    Published: 5/26/2025
18. Beyond Reward Hacking: Causal Rewards for Large LanguageModel Alignment

    Published: 5/26/2025
19. Learning How Hard to Think: Input-Adaptive Allocation of LM Computation

    Published: 5/26/2025
20. Highlighting What Matters: Promptable Embeddings for Attribute-Focused Image Retrieval

    Published: 5/26/2025