Best AI papers explained

519 Odcinki

1. Estimation of Treatment Effects Under Nonstationarity via Truncated Difference-in-Q’s

   Opublikowany: 12.06.2025
2. Strategy Coopetition Explains the Emergence and Transience of In-Context Learning

   Opublikowany: 12.06.2025
3. Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs

   Opublikowany: 11.06.2025
4. Agentic Supernet for Multi-agent Architecture Search

   Opublikowany: 11.06.2025
5. Sample Complexity and Representation Ability of Test-time Scaling Paradigms

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

   Opublikowany: 10.06.2025
7. LLMs Get Lost In Multi-Turn Conversation

   Opublikowany: 9.06.2025
8. PromptPex: Automatic Test Generation for Prompts

   Opublikowany: 8.06.2025
9. General Agents Need World Models

   Opublikowany: 8.06.2025
10. The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models

    Opublikowany: 7.06.2025
11. Decisions With Algorithms

    Opublikowany: 7.06.2025
12. Adapting, fast and slow: Causal Approach to Few-Shot Sequence Learning

    Opublikowany: 6.06.2025
13. Conformal Arbitrage for LLM Objective Balancing

    Opublikowany: 6.06.2025
14. Simulation-Based Inference for Adaptive Experiments

    Opublikowany: 6.06.2025
15. Agents as Tool-Use Decision-Makers

    Opublikowany: 6.06.2025
16. Quantitative Judges for Large Language Models

    Opublikowany: 6.06.2025
17. Self-Challenging Language Model Agents

    Opublikowany: 6.06.2025
18. Learning to Explore: An In-Context Learning Approach for Pure Exploration

    Opublikowany: 6.06.2025
19. How Bidirectionality Helps Language Models Learn Better via Dynamic Bottleneck Estimation

    Opublikowany: 6.06.2025
20. A Closer Look at Bias and Chain-of-Thought Faithfulness of Large (Vision) Language Models

    Opublikowany: 5.06.2025