Best AI papers explained

512 Episodo

1. A foundation model to predict and capture human cognition

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

    Publicado: 26/7/2025
18. Zuckerberg's AI Vision Analyzed

    Publicado: 26/7/2025
19. Inside Claude: Scaling, Agency, and Interpretability

    Publicado: 26/7/2025
20. Personalized language modeling from personalized human feedback

    Publicado: 26/7/2025