Best AI papers explained

481 Episodes

1. Learning to Explore: An In-Context Learning Approach for Pure Exploration

   Published: 7/3/2025
2. Human-AI Matching: The Limits of Algorithmic Search

   Published: 6/25/2025
3. Uncertainty Quantification Needs Reassessment for Large-language Model Agents

   Published: 6/25/2025
4. Bayesian Meta-Reasoning for Robust LLM Generalization

   Published: 6/25/2025
5. General Intelligence Requires Reward-based Pretraining

   Published: 6/25/2025
6. Deep Learning is Not So Mysterious or Different

   Published: 6/25/2025
7. AI Agents Need Authenticated Delegation

   Published: 6/25/2025
8. Probabilistic Modelling is Sufficient for Causal Inference

   Published: 6/25/2025
9. Not All Explanations for Deep Learning Phenomena Are Equally Valuable

   Published: 6/25/2025
10. e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs

    Published: 6/17/2025
11. Extrapolation by Association: Length Generalization Transfer in Transformers

    Published: 6/17/2025
12. Uncovering Causal Hierarchies in Language Model Capabilities

    Published: 6/17/2025
13. Generalization or Hallucination? Understanding Out-of-Context Reasoning in Transformers

    Published: 6/17/2025
14. Improving Treatment Effect Estimation with LLM-Based Data Augmentation

    Published: 6/17/2025
15. LLM Numerical Prediction Without Auto-Regression

    Published: 6/17/2025
16. Self-Adapting Language Models

    Published: 6/17/2025
17. Why in-context learning models are good few-shot learners?

    Published: 6/17/2025
18. Take Caution in Using LLMs as Human Surrogates: Scylla Ex Machina∗

    Published: 6/14/2025
19. The Logic of Machines: The AI Reasoning Debate

    Published: 6/12/2025
20. Layer by Layer: Uncovering Hidden Representations in Language Models

    Published: 6/12/2025