Best AI papers explained

456 Episodes

1. UFT: Unifying Supervised and Reinforcement Fine-Tuning

   Published: 5/26/2025
2. Understanding High-Dimensional Bayesian Optimization

   Published: 5/26/2025
3. Inference time alignment in continuous space

   Published: 5/25/2025
4. Efficient Test-Time Scaling via Self-Calibration

   Published: 5/25/2025
5. Conformal Prediction via Bayesian Quadrature

   Published: 5/25/2025
6. Predicting from Strings: Language Model Embeddings for Bayesian Optimization

   Published: 5/25/2025
7. Self-Evolving Curriculum for LLM Reasoning

   Published: 5/25/2025
8. Online Decision-Focused Learning in Dynamic Environments

   Published: 5/25/2025
9. FisherSFT: Data-Efficient Supervised Fine-Tuning of Language Models Using Information Gain

   Published: 5/25/2025
10. Reward Shaping from Confounded Offline Data

    Published: 5/25/2025
11. Trajectory Bellman Residual Minimization: A Simple Value-Based Method for LLM Reasoning

    Published: 5/25/2025
12. Understanding Best-of-N Language Model Alignment

    Published: 5/25/2025
13. Maximizing Acquisition Functions for Bayesian Optimization - and its relation to Gradient Descent

    Published: 5/24/2025
14. Bayesian Prompt Ensembles: Model Uncertainty Estimation for Black-Box Large Language Models

    Published: 5/24/2025
15. Prompting Strategies for Enabling Large Language Models to Infer Causation from Correlation

    Published: 5/24/2025
16. The Parallel Knowledge Gradient Method for Batch Bayesian Optimization

    Published: 5/24/2025
17. FunBO: Discovering Acquisition Functions for Bayesian Optimization with FunSearch

    Published: 5/24/2025
18. Automated Social Science: A Structural Causal Model-Based Approach

    Published: 5/24/2025
19. Causal Interpretation of Transformer Self-Attention

    Published: 5/24/2025
20. A Causal World Model Underlying Next Token Prediction: Exploring GPT in a Controlled Environment

    Published: 5/24/2025