Best AI papers explained

550 Avsnitt

1. The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models

   Publicerades: 2025-06-07
2. Decisions With Algorithms

   Publicerades: 2025-06-07
3. Adapting, fast and slow: Causal Approach to Few-Shot Sequence Learning

   Publicerades: 2025-06-06
4. Conformal Arbitrage for LLM Objective Balancing

   Publicerades: 2025-06-06
5. Simulation-Based Inference for Adaptive Experiments

   Publicerades: 2025-06-06
6. Agents as Tool-Use Decision-Makers

   Publicerades: 2025-06-06
7. Quantitative Judges for Large Language Models

   Publicerades: 2025-06-06
8. Self-Challenging Language Model Agents

   Publicerades: 2025-06-06
9. Learning to Explore: An In-Context Learning Approach for Pure Exploration

   Publicerades: 2025-06-06
10. How Bidirectionality Helps Language Models Learn Better via Dynamic Bottleneck Estimation

    Publicerades: 2025-06-06
11. A Closer Look at Bias and Chain-of-Thought Faithfulness of Large (Vision) Language Models

    Publicerades: 2025-06-05
12. Simplifying Bayesian Optimization Via In-Context Direct Optimum Sampling

    Publicerades: 2025-06-05
13. Bayesian Teaching Enables Probabilistic Reasoning in Large Language Models

    Publicerades: 2025-06-05
14. IPO: Interpretable Prompt Optimization for Vision-Language Models

    Publicerades: 2025-06-05
15. Evolutionary Prompt Optimization discovers emergent multimodal reasoning strategies

    Publicerades: 2025-06-05
16. Evaluating the Unseen Capabilities: How Many Theorems Do LLMs Know?

    Publicerades: 2025-06-04
17. Diffusion Guidance Is a Controllable Policy Improvement Operator

    Publicerades: 2025-06-02
18. Alita: Generalist Agent With Self-Evolution

    Publicerades: 2025-06-02
19. A Snapshot of Influence: A Local Data Attribution Framework for Online Reinforcement Learning

    Publicerades: 2025-06-02
20. Learning Compositional Functions with Transformers from Easy-to-Hard Data

    Publicerades: 2025-06-02