Best AI papers explained

550 Episoade

1. Uncovering Causal Hierarchies in Language Model Capabilities

   Publicat: 17.06.2025
2. Generalization or Hallucination? Understanding Out-of-Context Reasoning in Transformers

   Publicat: 17.06.2025
3. Improving Treatment Effect Estimation with LLM-Based Data Augmentation

   Publicat: 17.06.2025
4. LLM Numerical Prediction Without Auto-Regression

   Publicat: 17.06.2025
5. Self-Adapting Language Models

   Publicat: 17.06.2025
6. Why in-context learning models are good few-shot learners?

   Publicat: 17.06.2025
7. Take Caution in Using LLMs as Human Surrogates: Scylla Ex Machina∗

   Publicat: 14.06.2025
8. The Logic of Machines: The AI Reasoning Debate

   Publicat: 12.06.2025
9. Layer by Layer: Uncovering Hidden Representations in Language Models

   Publicat: 12.06.2025
10. Causal Attribution Analysis for Continuous Outcomes

    Publicat: 12.06.2025
11. Training a Generally Curious Agent

    Publicat: 12.06.2025
12. Estimation of Treatment Effects Under Nonstationarity via Truncated Difference-in-Q’s

    Publicat: 12.06.2025
13. Strategy Coopetition Explains the Emergence and Transience of In-Context Learning

    Publicat: 12.06.2025
14. Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs

    Publicat: 11.06.2025
15. Agentic Supernet for Multi-agent Architecture Search

    Publicat: 11.06.2025
16. Sample Complexity and Representation Ability of Test-time Scaling Paradigms

    Publicat: 11.06.2025
17. Aligning with Human Judgement: The Role of Pairwise Preference in Large Language Model Evaluators

    Publicat: 10.06.2025
18. LLMs Get Lost In Multi-Turn Conversation

    Publicat: 09.06.2025
19. PromptPex: Automatic Test Generation for Prompts

    Publicat: 08.06.2025
20. General Agents Need World Models

    Publicat: 08.06.2025