Best AI papers explained

484 Episodes

1. Bayesian Concept Bottlenecks with LLM Priors

   Published: 5/17/2025
2. Transformers for In-Context Reinforcement Learning

   Published: 5/17/2025
3. Evaluating Large Language Models Across the Lifecycle

   Published: 5/17/2025
4. Active Ranking from Human Feedback with DopeWolfe

   Published: 5/16/2025
5. Optimal Designs for Preference Elicitation

   Published: 5/16/2025
6. Dual Active Learning for Reinforcement Learning from Human Feedback

   Published: 5/16/2025
7. Active Learning for Direct Preference Optimization

   Published: 5/16/2025
8. Active Preference Optimization for RLHF

   Published: 5/16/2025
9. Test-Time Alignment of Diffusion Models without reward over-optimization

   Published: 5/16/2025
10. Test-Time Preference Optimization: On-the-Fly Alignment via Iterative Textual Feedback

    Published: 5/16/2025
11. GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-time Alignment

    Published: 5/16/2025
12. Advantage-Weighted Regression: Simple and Scalable Off-Policy RL

    Published: 5/16/2025
13. Can RLHF be More Efficient with Imperfect Reward Models? A Policy Coverage Perspective

    Published: 5/16/2025
14. Transformers can be used for in-context linear regression in the presence of endogeneity

    Published: 5/15/2025
15. Bayesian Concept Bottlenecks with LLM Priors

    Published: 5/15/2025
16. In-Context Parametric Inference: Point or Distribution Estimators?

    Published: 5/15/2025
17. Enough Coin Flips Can Make LLMs Act Bayesian

    Published: 5/15/2025
18. Bayesian Scaling Laws for In-Context Learning

    Published: 5/15/2025
19. Posterior Mean Matching Generative Modeling

    Published: 5/15/2025
20. Can Generative AI Solve Your In-Context Learning Problem? A Martingale Perspective

    Published: 5/15/2025