Best AI papers explained

499 Episodo

1. Uncertainty Quantification Needs Reassessment for Large-language Model Agents

   Publicado: 25/6/2025
2. Bayesian Meta-Reasoning for Robust LLM Generalization

   Publicado: 25/6/2025
3. General Intelligence Requires Reward-based Pretraining

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

   Publicado: 25/6/2025
5. AI Agents Need Authenticated Delegation

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

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

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

   Publicado: 17/6/2025
9. Extrapolation by Association: Length Generalization Transfer in Transformers

   Publicado: 17/6/2025
10. Uncovering Causal Hierarchies in Language Model Capabilities

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

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

    Publicado: 17/6/2025
13. LLM Numerical Prediction Without Auto-Regression

    Publicado: 17/6/2025
14. Self-Adapting Language Models

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

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

    Publicado: 14/6/2025
17. The Logic of Machines: The AI Reasoning Debate

    Publicado: 12/6/2025
18. Layer by Layer: Uncovering Hidden Representations in Language Models

    Publicado: 12/6/2025
19. Causal Attribution Analysis for Continuous Outcomes

    Publicado: 12/6/2025
20. Training a Generally Curious Agent

    Publicado: 12/6/2025