550 Episodo

  1. Bayesian Concept Bottlenecks with LLM Priors

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

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

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

    Publicado: 15/5/2025
  5. Posterior Mean Matching Generative Modeling

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

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

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

    Publicado: 12/5/2025
  9. Leaked Claude Sonnet 3.7 System Instruction tuning

    Publicado: 12/5/2025
  10. Converging Predictions with Shared Information

    Publicado: 11/5/2025
  11. Test-Time Alignment Via Hypothesis Reweighting

    Publicado: 11/5/2025
  12. Rethinking Diverse Human Preference Learning through Principal Component Analysis

    Publicado: 11/5/2025
  13. Active Statistical Inference

    Publicado: 10/5/2025
  14. Data Mixture Optimization: A Multi-fidelity Multi-scale Bayesian Framework

    Publicado: 10/5/2025
  15. AI-Powered Bayesian Inference

    Publicado: 10/5/2025
  16. Can Unconfident LLM Annotations Be Used for Confident Conclusions?

    Publicado: 9/5/2025
  17. Predictions as Surrogates: Revisiting Surrogate Outcomes in the Age of AI

    Publicado: 9/5/2025
  18. Learn then Test: Calibrating Predictive Algorithms to Achieve Risk Control

    Publicado: 9/5/2025
  19. How to Evaluate Reward Models for RLHF

    Publicado: 9/5/2025
  20. LLMs as Judges: Survey of Evaluation Methods

    Publicado: 9/5/2025

19 / 28

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

Visit the podcast's native language site