Best AI papers explained

550 Episodes

1. How do LLMs use their depth?

   Published: 10/27/2025
2. Thought Communication in Multiagent Collaboration

   Published: 10/27/2025
3. Reasoning with Sampling: Base Models Outperform RL

   Published: 10/26/2025
4. Continual Learning via Sparse Memory Finetuning

   Published: 10/26/2025
5. Direct Preference Optimization with Unobserved Preference Heterogeneity: The Necessity of Ternary Preferences

   Published: 10/24/2025
6. The Coverage Principle: How Pre-Training Enables Post-Training

   Published: 10/24/2025
7. The Era of Real-World Human Interaction: RL from User Conversations

   Published: 10/24/2025
8. Agent Learning via Early Experience

   Published: 10/24/2025
9. Demystifying the Mechanisms Behind Emergent Exploration in Goal-conditioned RL

   Published: 10/22/2025
10. Rewriting History: A Recipe for Interventional Analyses to Study Data Effects on Model Behavior

    Published: 10/22/2025
11. A Definition of AGI

    Published: 10/22/2025
12. Provably Learning from Language Feedback

    Published: 10/21/2025
13. In-Context Learning for Pure Exploration

    Published: 10/21/2025
14. On the Role of Preference Variance in Preference Optimization

    Published: 10/20/2025
15. Training LLM Agents to Empower Humans

    Published: 10/20/2025
16. Richard Sutton Declares LLMs a Dead End

    Published: 10/20/2025
17. Demystifying Reinforcement Learning in Agentic Reasoning

    Published: 10/19/2025
18. Emergent coordination in multi-agent language models

    Published: 10/19/2025
19. Learning-to-measure: in-context active feature acquisition

    Published: 10/19/2025
20. Andrej Karpathy's insights: AGI, Intelligence, and Evolution

    Published: 10/19/2025