Best AI papers explained

442 Episodes

1. Context Engineering: Beyond Simple Prompting to LLM Architecture

   Published: 7/28/2025
2. Agentic Misalignment: LLMs as Insider Threats

   Published: 7/28/2025
3. Small Language Models: Future of Agentic AI

   Published: 7/28/2025
4. Learning without training: The implicit dynamics of in-context learning

   Published: 7/28/2025
5. Inverse Scaling in Test-Time Compute

   Published: 7/28/2025
6. LLM Economist: Large Population Models and Mechanism Design in Multi-Agent Generative Simulacra

   Published: 7/28/2025
7. Microsoft's Blueprint: AI, Quantum, and the Agentic Future

   Published: 7/26/2025
8. Zuckerberg's AI Vision Analyzed

   Published: 7/26/2025
9. Inside Claude: Scaling, Agency, and Interpretability

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

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

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

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

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

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

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

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

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

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

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

    Published: 7/15/2025