Best AI papers explained

550 Episoade

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

   Publicat: 07.06.2025
2. Decisions With Algorithms

   Publicat: 07.06.2025
3. Adapting, fast and slow: Causal Approach to Few-Shot Sequence Learning

   Publicat: 06.06.2025
4. Conformal Arbitrage for LLM Objective Balancing

   Publicat: 06.06.2025
5. Simulation-Based Inference for Adaptive Experiments

   Publicat: 06.06.2025
6. Agents as Tool-Use Decision-Makers

   Publicat: 06.06.2025
7. Quantitative Judges for Large Language Models

   Publicat: 06.06.2025
8. Self-Challenging Language Model Agents

   Publicat: 06.06.2025
9. Learning to Explore: An In-Context Learning Approach for Pure Exploration

   Publicat: 06.06.2025
10. How Bidirectionality Helps Language Models Learn Better via Dynamic Bottleneck Estimation

    Publicat: 06.06.2025
11. A Closer Look at Bias and Chain-of-Thought Faithfulness of Large (Vision) Language Models

    Publicat: 05.06.2025
12. Simplifying Bayesian Optimization Via In-Context Direct Optimum Sampling

    Publicat: 05.06.2025
13. Bayesian Teaching Enables Probabilistic Reasoning in Large Language Models

    Publicat: 05.06.2025
14. IPO: Interpretable Prompt Optimization for Vision-Language Models

    Publicat: 05.06.2025
15. Evolutionary Prompt Optimization discovers emergent multimodal reasoning strategies

    Publicat: 05.06.2025
16. Evaluating the Unseen Capabilities: How Many Theorems Do LLMs Know?

    Publicat: 04.06.2025
17. Diffusion Guidance Is a Controllable Policy Improvement Operator

    Publicat: 02.06.2025
18. Alita: Generalist Agent With Self-Evolution

    Publicat: 02.06.2025
19. A Snapshot of Influence: A Local Data Attribution Framework for Online Reinforcement Learning

    Publicat: 02.06.2025
20. Learning Compositional Functions with Transformers from Easy-to-Hard Data

    Publicat: 02.06.2025