Best AI papers explained

550 Avsnitt

1. Uncovering Causal Hierarchies in Language Model Capabilities

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

   Publicerades: 2025-06-17
3. Improving Treatment Effect Estimation with LLM-Based Data Augmentation

   Publicerades: 2025-06-17
4. LLM Numerical Prediction Without Auto-Regression

   Publicerades: 2025-06-17
5. Self-Adapting Language Models

   Publicerades: 2025-06-17
6. Why in-context learning models are good few-shot learners?

   Publicerades: 2025-06-17
7. Take Caution in Using LLMs as Human Surrogates: Scylla Ex Machina∗

   Publicerades: 2025-06-14
8. The Logic of Machines: The AI Reasoning Debate

   Publicerades: 2025-06-12
9. Layer by Layer: Uncovering Hidden Representations in Language Models

   Publicerades: 2025-06-12
10. Causal Attribution Analysis for Continuous Outcomes

    Publicerades: 2025-06-12
11. Training a Generally Curious Agent

    Publicerades: 2025-06-12
12. Estimation of Treatment Effects Under Nonstationarity via Truncated Difference-in-Q’s

    Publicerades: 2025-06-12
13. Strategy Coopetition Explains the Emergence and Transience of In-Context Learning

    Publicerades: 2025-06-12
14. Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs

    Publicerades: 2025-06-11
15. Agentic Supernet for Multi-agent Architecture Search

    Publicerades: 2025-06-11
16. Sample Complexity and Representation Ability of Test-time Scaling Paradigms

    Publicerades: 2025-06-11
17. Aligning with Human Judgement: The Role of Pairwise Preference in Large Language Model Evaluators

    Publicerades: 2025-06-10
18. LLMs Get Lost In Multi-Turn Conversation

    Publicerades: 2025-06-09
19. PromptPex: Automatic Test Generation for Prompts

    Publicerades: 2025-06-08
20. General Agents Need World Models

    Publicerades: 2025-06-08