Best AI papers explained

456 Episodes

1. AI-Powered Bayesian Inference

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

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

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

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

   Published: 5/9/2025
6. LLMs as Judges: Survey of Evaluation Methods

   Published: 5/9/2025
7. The Alternative Annotator Test for LLM-as-a-Judge: How to Statistically Justify Replacing Human Annotators with LLMs

   Published: 5/9/2025
8. Limits to scalable evaluation at the frontier: LLM as Judge won’t beat twice the data

   Published: 5/9/2025
9. Stratified Prediction-Powered Inference for Hybrid Language Model Evaluation

   Published: 5/9/2025
10. Accelerating Unbiased LLM Evaluation via Synthetic Feedback

    Published: 5/9/2025
11. Prediction-Powered Statistical Inference Framework

    Published: 5/9/2025
12. Optimizing Chain-of-Thought Reasoners via Gradient Variance Minimization in Rejection Sampling and RL

    Published: 5/9/2025
13. RM-R1: Reward Modeling as Reasoning

    Published: 5/9/2025
14. Reexamining the Aleatoric and Epistemic Uncertainty Dichotomy

    Published: 5/8/2025
15. Decoding Claude Code: Terminal Agent for Developers

    Published: 5/7/2025
16. Emergent Strategic AI Equilibrium from Pre-trained Reasoning

    Published: 5/7/2025
17. Benefiting from Proprietary Data with Siloed Training

    Published: 5/6/2025
18. Advantage Alignment Algorithms

    Published: 5/6/2025
19. Asymptotic Safety Guarantees Based On Scalable Oversight

    Published: 5/6/2025
20. What Makes a Reward Model a Good Teacher? An Optimization Perspective

    Published: 5/6/2025