Best AI papers explained

523 Episodes

1. From AI-Curious to AI-First: Engineering Production AI Systems

   Published: 28/07/2025
2. Context Engineering: Beyond Simple Prompting to LLM Architecture

   Published: 28/07/2025
3. Agentic Misalignment: LLMs as Insider Threats

   Published: 28/07/2025
4. Small Language Models: Future of Agentic AI

   Published: 28/07/2025
5. Learning without training: The implicit dynamics of in-context learning

   Published: 28/07/2025
6. Inverse Scaling in Test-Time Compute

   Published: 28/07/2025
7. LLM Economist: Large Population Models and Mechanism Design in Multi-Agent Generative Simulacra

   Published: 28/07/2025
8. Microsoft's Blueprint: AI, Quantum, and the Agentic Future

   Published: 26/07/2025
9. Zuckerberg's AI Vision Analyzed

   Published: 26/07/2025
10. Inside Claude: Scaling, Agency, and Interpretability

    Published: 26/07/2025
11. Personalized language modeling from personalized human feedback

    Published: 26/07/2025
12. Position: Empowering Time Series Reasoning with Multimodal LLMs

    Published: 25/07/2025
13. An empirical risk minimization approach for offline inverse RL and Dynamic Discrete Choice models

    Published: 22/07/2025
14. Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities

    Published: 22/07/2025
15. The Invisible Leash: Why RLVR May Not Escape Its Origin

    Published: 20/07/2025
16. Language Model Personalization via Reward Factorization

    Published: 20/07/2025
17. Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked Diffusions

    Published: 18/07/2025
18. Do We Need to Verify Step by Step? Rethinking Process Supervision from a Theoretical Perspective

    Published: 17/07/2025
19. Soft Best-of-n Sampling for Model Alignment

    Published: 16/07/2025
20. On Temporal Credit Assignment and Data-Efficient Reinforcement Learning

    Published: 15/07/2025