Best AI papers explained

428 Episodes

1. Systematic Meta-Abilities Alignment in Large Reasoning Models

   Published: 5/20/2025
2. Predictability Shapes Adaptation: An Evolutionary Perspective on Modes of Learning in Transformers

   Published: 5/20/2025
3. Efficient Exploration for LLMs

   Published: 5/19/2025
4. Rankers, Judges, and Assistants: Towards Understanding the Interplay of LLMs in Information Retrieval Evaluation

   Published: 5/18/2025
5. Bayesian Concept Bottlenecks with LLM Priors

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

    Published: 5/15/2025