Best AI papers explained

525 Odcinki

1. Can Generative AI Solve Your In-Context Learning Problem? A Martingale Perspective

   Opublikowany: 15.05.2025
2. Dynamic Search for Inference-Time Alignment in Diffusion Models

   Opublikowany: 15.05.2025
3. Is In-Context Learning in Large Language Models Bayesian? A Martingale Perspective

   Opublikowany: 12.05.2025
4. Leaked Claude Sonnet 3.7 System Instruction tuning

   Opublikowany: 12.05.2025
5. Converging Predictions with Shared Information

   Opublikowany: 11.05.2025
6. Test-Time Alignment Via Hypothesis Reweighting

   Opublikowany: 11.05.2025
7. Rethinking Diverse Human Preference Learning through Principal Component Analysis

   Opublikowany: 11.05.2025
8. Active Statistical Inference

   Opublikowany: 10.05.2025
9. Data Mixture Optimization: A Multi-fidelity Multi-scale Bayesian Framework

   Opublikowany: 10.05.2025
10. AI-Powered Bayesian Inference

    Opublikowany: 10.05.2025
11. Can Unconfident LLM Annotations Be Used for Confident Conclusions?

    Opublikowany: 9.05.2025
12. Predictions as Surrogates: Revisiting Surrogate Outcomes in the Age of AI

    Opublikowany: 9.05.2025
13. Learn then Test: Calibrating Predictive Algorithms to Achieve Risk Control

    Opublikowany: 9.05.2025
14. How to Evaluate Reward Models for RLHF

    Opublikowany: 9.05.2025
15. LLMs as Judges: Survey of Evaluation Methods

    Opublikowany: 9.05.2025
16. The Alternative Annotator Test for LLM-as-a-Judge: How to Statistically Justify Replacing Human Annotators with LLMs

    Opublikowany: 9.05.2025
17. Limits to scalable evaluation at the frontier: LLM as Judge won’t beat twice the data

    Opublikowany: 9.05.2025
18. Stratified Prediction-Powered Inference for Hybrid Language Model Evaluation

    Opublikowany: 9.05.2025
19. Accelerating Unbiased LLM Evaluation via Synthetic Feedback

    Opublikowany: 9.05.2025
20. Prediction-Powered Statistical Inference Framework

    Opublikowany: 9.05.2025