Best AI papers explained

442 Episodes

1. Evaluating Large Language Models Across the Lifecycle

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

    Published: 5/15/2025
19. Dynamic Search for Inference-Time Alignment in Diffusion Models

    Published: 5/15/2025
20. Is In-Context Learning in Large Language Models Bayesian? A Martingale Perspective

    Published: 5/12/2025