Best AI papers explained

525 Episodes

1. Embodied AI Agents: Modeling the World

   Published: 4/07/2025
2. Beyond Statistical Learning: Exact Learning Is Essential for General Intelligence

   Published: 4/07/2025
3. What Has a Foundation Model Found? Inductive Bias Reveals World Models

   Published: 4/07/2025
4. Language Bottleneck Models: A Framework for Interpretable Knowledge Tracing and Beyond

   Published: 3/07/2025
5. Learning to Explore: An In-Context Learning Approach for Pure Exploration

   Published: 3/07/2025
6. Human-AI Matching: The Limits of Algorithmic Search

   Published: 25/06/2025
7. Uncertainty Quantification Needs Reassessment for Large-language Model Agents

   Published: 25/06/2025
8. Bayesian Meta-Reasoning for Robust LLM Generalization

   Published: 25/06/2025
9. General Intelligence Requires Reward-based Pretraining

   Published: 25/06/2025
10. Deep Learning is Not So Mysterious or Different

    Published: 25/06/2025
11. AI Agents Need Authenticated Delegation

    Published: 25/06/2025
12. Probabilistic Modelling is Sufficient for Causal Inference

    Published: 25/06/2025
13. Not All Explanations for Deep Learning Phenomena Are Equally Valuable

    Published: 25/06/2025
14. e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs

    Published: 17/06/2025
15. Extrapolation by Association: Length Generalization Transfer in Transformers

    Published: 17/06/2025
16. Uncovering Causal Hierarchies in Language Model Capabilities

    Published: 17/06/2025
17. Generalization or Hallucination? Understanding Out-of-Context Reasoning in Transformers

    Published: 17/06/2025
18. Improving Treatment Effect Estimation with LLM-Based Data Augmentation

    Published: 17/06/2025
19. LLM Numerical Prediction Without Auto-Regression

    Published: 17/06/2025
20. Self-Adapting Language Models

    Published: 17/06/2025