Best AI papers explained

515 Episoade

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

   Publicat: 06.08.2025
2. Statistical Rigor for Interpretable AI

   Publicat: 06.08.2025
3. Full-Stack Alignment: Co-Aligning AI and Institutions with Thick Models of Value

   Publicat: 04.08.2025
4. A foundation model to predict and capture human cognition

   Publicat: 04.08.2025
5. Generative Recommendation with Semantic IDs: A Practitioner’s Handbook

   Publicat: 04.08.2025
6. Hierarchical Reasoning Model

   Publicat: 04.08.2025
7. Test-time Offline Reinforcement Learning on Goal-related Experience

   Publicat: 04.08.2025
8. Interpreting Chain of Thought: A Walkthrough and Discussion

   Publicat: 04.08.2025
9. The wall confronting large language models

   Publicat: 04.08.2025
10. COLLABLLM: LLMs From Passive to Collaborative

    Publicat: 31.07.2025
11. A decade's battle on dataset bias: are we there yet?

    Publicat: 29.07.2025
12. GEPA: Generative Feedback for AI System Optimization

    Publicat: 29.07.2025
13. From AI-Curious to AI-First: Engineering Production AI Systems

    Publicat: 28.07.2025
14. Context Engineering: Beyond Simple Prompting to LLM Architecture

    Publicat: 28.07.2025
15. Agentic Misalignment: LLMs as Insider Threats

    Publicat: 28.07.2025
16. Small Language Models: Future of Agentic AI

    Publicat: 28.07.2025
17. Learning without training: The implicit dynamics of in-context learning

    Publicat: 28.07.2025
18. Inverse Scaling in Test-Time Compute

    Publicat: 28.07.2025
19. LLM Economist: Large Population Models and Mechanism Design in Multi-Agent Generative Simulacra

    Publicat: 28.07.2025
20. Microsoft's Blueprint: AI, Quantum, and the Agentic Future

    Publicat: 26.07.2025