Best AI papers explained

534 Episodes

1. Demystifying Reinforcement Learning in Agentic Reasoning

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

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

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

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

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

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

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

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

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

    Published: 10/16/2025
11. Dual Goal Representations

    Published: 10/14/2025
12. Welcome to the Era of Experience

    Published: 10/14/2025
13. Value Flows: Flow-Based Distributional Reinforcement Learning

    Published: 10/14/2025
14. Self-Adapting Language Models

    Published: 10/12/2025
15. The Markovian Thinker

    Published: 10/12/2025
16. Moloch’s Bargain: emergent misalignment when LLMs compete for audiences

    Published: 10/12/2025
17. Transformer Predictor Dynamics and Task Diversity

    Published: 10/11/2025
18. Base models know how to reason, thinking models learn when

    Published: 10/11/2025
19. Spectrum tuning: Post-training for distributional coverage and in-context steerability

    Published: 10/11/2025
20. Understanding Prompt Tuning and In-Context Learning via Meta-Learning

    Published: 10/11/2025