Best AI papers explained

440 Episodo

1. Optimal Designs for Preference Elicitation

   Publicado: 16/5/2025
2. Dual Active Learning for Reinforcement Learning from Human Feedback

   Publicado: 16/5/2025
3. Active Learning for Direct Preference Optimization

   Publicado: 16/5/2025
4. Active Preference Optimization for RLHF

   Publicado: 16/5/2025
5. Test-Time Alignment of Diffusion Models without reward over-optimization

   Publicado: 16/5/2025
6. Test-Time Preference Optimization: On-the-Fly Alignment via Iterative Textual Feedback

   Publicado: 16/5/2025
7. GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-time Alignment

   Publicado: 16/5/2025
8. Advantage-Weighted Regression: Simple and Scalable Off-Policy RL

   Publicado: 16/5/2025
9. Can RLHF be More Efficient with Imperfect Reward Models? A Policy Coverage Perspective

   Publicado: 16/5/2025
10. Transformers can be used for in-context linear regression in the presence of endogeneity

    Publicado: 15/5/2025
11. Bayesian Concept Bottlenecks with LLM Priors

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

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

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

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

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

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

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

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

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

    Publicado: 11/5/2025