Best AI papers explained

490 Episoder

1. Hierarchical Reasoning Model

   Publisert: 4.8.2025
2. Test-time Offline Reinforcement Learning on Goal-related Experience

   Publisert: 4.8.2025
3. Interpreting Chain of Thought: A Walkthrough and Discussion

   Publisert: 4.8.2025
4. The wall confronting large language models

   Publisert: 4.8.2025
5. COLLABLLM: LLMs From Passive to Collaborative

   Publisert: 31.7.2025
6. A decade's battle on dataset bias: are we there yet?

   Publisert: 29.7.2025
7. GEPA: Generative Feedback for AI System Optimization

   Publisert: 29.7.2025
8. From AI-Curious to AI-First: Engineering Production AI Systems

   Publisert: 28.7.2025
9. Context Engineering: Beyond Simple Prompting to LLM Architecture

   Publisert: 28.7.2025
10. Agentic Misalignment: LLMs as Insider Threats

    Publisert: 28.7.2025
11. Small Language Models: Future of Agentic AI

    Publisert: 28.7.2025
12. Learning without training: The implicit dynamics of in-context learning

    Publisert: 28.7.2025
13. Inverse Scaling in Test-Time Compute

    Publisert: 28.7.2025
14. LLM Economist: Large Population Models and Mechanism Design in Multi-Agent Generative Simulacra

    Publisert: 28.7.2025
15. Microsoft's Blueprint: AI, Quantum, and the Agentic Future

    Publisert: 26.7.2025
16. Zuckerberg's AI Vision Analyzed

    Publisert: 26.7.2025
17. Inside Claude: Scaling, Agency, and Interpretability

    Publisert: 26.7.2025
18. Personalized language modeling from personalized human feedback

    Publisert: 26.7.2025
19. Position: Empowering Time Series Reasoning with Multimodal LLMs

    Publisert: 25.7.2025
20. An empirical risk minimization approach for offline inverse RL and Dynamic Discrete Choice models

    Publisert: 22.7.2025