521 Afleveringen

  1. Rewriting History: A Recipe for Interventional Analyses to Study Data Effects on Model Behavior

    Gepubliceerd: 22-10-2025
  2. A Definition of AGI

    Gepubliceerd: 22-10-2025
  3. Provably Learning from Language Feedback

    Gepubliceerd: 21-10-2025
  4. In-Context Learning for Pure Exploration

    Gepubliceerd: 21-10-2025
  5. On the Role of Preference Variance in Preference Optimization

    Gepubliceerd: 20-10-2025
  6. Training LLM Agents to Empower Humans

    Gepubliceerd: 20-10-2025
  7. Richard Sutton Declares LLMs a Dead End

    Gepubliceerd: 20-10-2025
  8. Demystifying Reinforcement Learning in Agentic Reasoning

    Gepubliceerd: 19-10-2025
  9. Emergent coordination in multi-agent language models

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

    Gepubliceerd: 19-10-2025
  11. Andrej Karpathy's insights: AGI, Intelligence, and Evolution

    Gepubliceerd: 19-10-2025
  12. Front-Loading Reasoning: The Synergy between Pretraining and Post-Training Data

    Gepubliceerd: 18-10-2025
  13. Representation-Based Exploration for Language Models: From Test-Time to Post-Training

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

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

    Gepubliceerd: 16-10-2025
  16. The Art of Scaling Reinforcement Learning Compute for LLMs

    Gepubliceerd: 16-10-2025
  17. A small number of samples can poison LLMs of any size

    Gepubliceerd: 16-10-2025
  18. Dual Goal Representations

    Gepubliceerd: 14-10-2025
  19. Welcome to the Era of Experience

    Gepubliceerd: 14-10-2025
  20. Value Flows: Flow-Based Distributional Reinforcement Learning

    Gepubliceerd: 14-10-2025

2 / 27

Cut through the noise. We curate and break down the most important AI papers so you don’t have to.

Visit the podcast's native language site