Best AI papers explained

454 Episodes

1. Statistical Rigor for Interpretable AI

   Published: 8/6/2025
2. Full-Stack Alignment: Co-Aligning AI and Institutions with Thick Models of Value

   Published: 8/4/2025
3. A foundation model to predict and capture human cognition

   Published: 8/4/2025
4. Generative Recommendation with Semantic IDs: A Practitioner’s Handbook

   Published: 8/4/2025
5. Hierarchical Reasoning Model

   Published: 8/4/2025
6. Test-time Offline Reinforcement Learning on Goal-related Experience

   Published: 8/4/2025
7. Interpreting Chain of Thought: A Walkthrough and Discussion

   Published: 8/4/2025
8. The wall confronting large language models

   Published: 8/4/2025
9. COLLABLLM: LLMs From Passive to Collaborative

   Published: 7/31/2025
10. A decade's battle on dataset bias: are we there yet?

    Published: 7/29/2025
11. GEPA: Generative Feedback for AI System Optimization

    Published: 7/29/2025
12. From AI-Curious to AI-First: Engineering Production AI Systems

    Published: 7/28/2025
13. Context Engineering: Beyond Simple Prompting to LLM Architecture

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

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

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

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

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

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

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

    Published: 7/26/2025