512 Episoder

  1. Learning-to-measure: in-context active feature acquisition

    Udgivet: 19.10.2025
  2. Andrej Karpathy's insights: AGI, Intelligence, and Evolution

    Udgivet: 19.10.2025
  3. Front-Loading Reasoning: The Synergy between Pretraining and Post-Training Data

    Udgivet: 18.10.2025
  4. Representation-Based Exploration for Language Models: From Test-Time to Post-Training

    Udgivet: 18.10.2025
  5. The attacker moves second: stronger adaptive attacks bypass defenses against LLM jail- Breaks and prompt injections

    Udgivet: 18.10.2025
  6. When can in-context learning generalize out of task distribution?

    Udgivet: 16.10.2025
  7. The Art of Scaling Reinforcement Learning Compute for LLMs

    Udgivet: 16.10.2025
  8. A small number of samples can poison LLMs of any size

    Udgivet: 16.10.2025
  9. Dual Goal Representations

    Udgivet: 14.10.2025
  10. Welcome to the Era of Experience

    Udgivet: 14.10.2025
  11. Value Flows: Flow-Based Distributional Reinforcement Learning

    Udgivet: 14.10.2025
  12. Self-Adapting Language Models

    Udgivet: 12.10.2025
  13. The Markovian Thinker

    Udgivet: 12.10.2025
  14. Moloch’s Bargain: emergent misalignment when LLMs compete for audiences

    Udgivet: 12.10.2025
  15. Transformer Predictor Dynamics and Task Diversity

    Udgivet: 11.10.2025
  16. Base models know how to reason, thinking models learn when

    Udgivet: 11.10.2025
  17. Spectrum tuning: Post-training for distributional coverage and in-context steerability

    Udgivet: 11.10.2025
  18. Understanding Prompt Tuning and In-Context Learning via Meta-Learning

    Udgivet: 11.10.2025
  19. MLPs Learn In-Context on Regression and Classification tasks

    Udgivet: 11.10.2025
  20. Is Pre-Training Truly Better than Meta-Learning?

    Udgivet: 11.10.2025

2 / 26

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