Best AI papers explained

454 Episodes

1. Inside Claude: Scaling, Agency, and Interpretability

   Published: 7/26/2025
2. Personalized language modeling from personalized human feedback

   Published: 7/26/2025
3. Position: Empowering Time Series Reasoning with Multimodal LLMs

   Published: 7/25/2025
4. An empirical risk minimization approach for offline inverse RL and Dynamic Discrete Choice models

   Published: 7/22/2025
5. Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities

   Published: 7/22/2025
6. The Invisible Leash: Why RLVR May Not Escape Its Origin

   Published: 7/20/2025
7. Language Model Personalization via Reward Factorization

   Published: 7/20/2025
8. Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked Diffusions

   Published: 7/18/2025
9. Do We Need to Verify Step by Step? Rethinking Process Supervision from a Theoretical Perspective

   Published: 7/17/2025
10. Soft Best-of-n Sampling for Model Alignment

    Published: 7/16/2025
11. On Temporal Credit Assignment and Data-Efficient Reinforcement Learning

    Published: 7/15/2025
12. Bradley–Terry and Multi-Objective Reward Modeling Are Complementary

    Published: 7/15/2025
13. Probing Foundation Models for World Models

    Published: 7/15/2025
14. GenAI-Powered Statistical Inference (with Unstructured Data)

    Published: 7/14/2025
15. Interpretable Reward Modeling with Active Concept Bottlenecks

    Published: 7/14/2025
16. PrefillOnly: An Inference Engine for Prefill-only Workloads in Large Language Model Applications

    Published: 7/14/2025
17. A Collectivist, Economic Perspective on AI

    Published: 7/14/2025
18. Textual Bayes: Quantifying Uncertainty in LLM-Based Systems

    Published: 7/12/2025
19. The Winner's Curse in Data-Driven Decisions

    Published: 7/11/2025
20. SPIRAL: Self-Play for Reasoning Through Zero-Sum Games

    Published: 7/11/2025