481 Episodes

  1. Active Ranking from Human Feedback with DopeWolfe

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

    Published: 5/12/2025
  20. Leaked Claude Sonnet 3.7 System Instruction tuning

    Published: 5/12/2025

15 / 25

Cut through the noise. We curate and break down the most important AI papers so you don’t have to.