Best AI papers explained

203 Episodes

1. Transformers for In-Context Reinforcement Learning

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

    Published: 5/15/2025