Best AI papers explained

515 Episodo

1. The Minimalist AI Kernel: A New Frontier in Reasoning

   Publicado: 6/8/2025
2. Statistical Rigor for Interpretable AI

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

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

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

   Publicado: 4/8/2025
6. Hierarchical Reasoning Model

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

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

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

   Publicado: 4/8/2025
10. COLLABLLM: LLMs From Passive to Collaborative

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

    Publicado: 29/7/2025
12. GEPA: Generative Feedback for AI System Optimization

    Publicado: 29/7/2025
13. From AI-Curious to AI-First: Engineering Production AI Systems

    Publicado: 28/7/2025
14. Context Engineering: Beyond Simple Prompting to LLM Architecture

    Publicado: 28/7/2025
15. Agentic Misalignment: LLMs as Insider Threats

    Publicado: 28/7/2025
16. Small Language Models: Future of Agentic AI

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

    Publicado: 28/7/2025
18. Inverse Scaling in Test-Time Compute

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

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

    Publicado: 26/7/2025