Best AI papers explained

550 Avsnitt

1. Bayesian Concept Bottlenecks with LLM Priors

   Publicerades: 2025-05-15
2. In-Context Parametric Inference: Point or Distribution Estimators?

   Publicerades: 2025-05-15
3. Enough Coin Flips Can Make LLMs Act Bayesian

   Publicerades: 2025-05-15
4. Bayesian Scaling Laws for In-Context Learning

   Publicerades: 2025-05-15
5. Posterior Mean Matching Generative Modeling

   Publicerades: 2025-05-15
6. Can Generative AI Solve Your In-Context Learning Problem? A Martingale Perspective

   Publicerades: 2025-05-15
7. Dynamic Search for Inference-Time Alignment in Diffusion Models

   Publicerades: 2025-05-15
8. Is In-Context Learning in Large Language Models Bayesian? A Martingale Perspective

   Publicerades: 2025-05-12
9. Leaked Claude Sonnet 3.7 System Instruction tuning

   Publicerades: 2025-05-12
10. Converging Predictions with Shared Information

    Publicerades: 2025-05-11
11. Test-Time Alignment Via Hypothesis Reweighting

    Publicerades: 2025-05-11
12. Rethinking Diverse Human Preference Learning through Principal Component Analysis

    Publicerades: 2025-05-11
13. Active Statistical Inference

    Publicerades: 2025-05-10
14. Data Mixture Optimization: A Multi-fidelity Multi-scale Bayesian Framework

    Publicerades: 2025-05-10
15. AI-Powered Bayesian Inference

    Publicerades: 2025-05-10
16. Can Unconfident LLM Annotations Be Used for Confident Conclusions?

    Publicerades: 2025-05-09
17. Predictions as Surrogates: Revisiting Surrogate Outcomes in the Age of AI

    Publicerades: 2025-05-09
18. Learn then Test: Calibrating Predictive Algorithms to Achieve Risk Control

    Publicerades: 2025-05-09
19. How to Evaluate Reward Models for RLHF

    Publicerades: 2025-05-09
20. LLMs as Judges: Survey of Evaluation Methods

    Publicerades: 2025-05-09