Best AI papers explained

520 Episodio

1. Human-AI Matching: The Limits of Algorithmic Search

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

   Pubblicato: 25/06/2025
3. Bayesian Meta-Reasoning for Robust LLM Generalization

   Pubblicato: 25/06/2025
4. General Intelligence Requires Reward-based Pretraining

   Pubblicato: 25/06/2025
5. Deep Learning is Not So Mysterious or Different

   Pubblicato: 25/06/2025
6. AI Agents Need Authenticated Delegation

   Pubblicato: 25/06/2025
7. Probabilistic Modelling is Sufficient for Causal Inference

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

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

   Pubblicato: 17/06/2025
10. Extrapolation by Association: Length Generalization Transfer in Transformers

    Pubblicato: 17/06/2025
11. Uncovering Causal Hierarchies in Language Model Capabilities

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

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

    Pubblicato: 17/06/2025
14. LLM Numerical Prediction Without Auto-Regression

    Pubblicato: 17/06/2025
15. Self-Adapting Language Models

    Pubblicato: 17/06/2025
16. Why in-context learning models are good few-shot learners?

    Pubblicato: 17/06/2025
17. Take Caution in Using LLMs as Human Surrogates: Scylla Ex Machina∗

    Pubblicato: 14/06/2025
18. The Logic of Machines: The AI Reasoning Debate

    Pubblicato: 12/06/2025
19. Layer by Layer: Uncovering Hidden Representations in Language Models

    Pubblicato: 12/06/2025
20. Causal Attribution Analysis for Continuous Outcomes

    Pubblicato: 12/06/2025