Best AI papers explained

544 Episodes

1. The Era of Real-World Human Interaction: RL from User Conversations

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

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

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

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

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

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

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

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

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

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

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

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

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

    Published: 10/19/2025
15. Front-Loading Reasoning: The Synergy between Pretraining and Post-Training Data

    Published: 10/18/2025
16. Representation-Based Exploration for Language Models: From Test-Time to Post-Training

    Published: 10/18/2025
17. The attacker moves second: stronger adaptive attacks bypass defenses against LLM jail- Breaks and prompt injections

    Published: 10/18/2025
18. When can in-context learning generalize out of task distribution?

    Published: 10/16/2025
19. The Art of Scaling Reinforcement Learning Compute for LLMs

    Published: 10/16/2025
20. A small number of samples can poison LLMs of any size

    Published: 10/16/2025