Best AI papers explained

525 Épisodes

1. A decade's battle on dataset bias: are we there yet?

   Publié: 29/07/2025
2. GEPA: Generative Feedback for AI System Optimization

   Publié: 29/07/2025
3. From AI-Curious to AI-First: Engineering Production AI Systems

   Publié: 28/07/2025
4. Context Engineering: Beyond Simple Prompting to LLM Architecture

   Publié: 28/07/2025
5. Agentic Misalignment: LLMs as Insider Threats

   Publié: 28/07/2025
6. Small Language Models: Future of Agentic AI

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

   Publié: 28/07/2025
8. Inverse Scaling in Test-Time Compute

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

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

    Publié: 26/07/2025
11. Zuckerberg's AI Vision Analyzed

    Publié: 26/07/2025
12. Inside Claude: Scaling, Agency, and Interpretability

    Publié: 26/07/2025
13. Personalized language modeling from personalized human feedback

    Publié: 26/07/2025
14. Position: Empowering Time Series Reasoning with Multimodal LLMs

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

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

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

    Publié: 20/07/2025
18. Language Model Personalization via Reward Factorization

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

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

    Publié: 17/07/2025