Best AI papers explained

502 Episodo

1. Learning to Explore: An In-Context Learning Approach for Pure Exploration

   Publicado: 6/6/2025
2. How Bidirectionality Helps Language Models Learn Better via Dynamic Bottleneck Estimation

   Publicado: 6/6/2025
3. A Closer Look at Bias and Chain-of-Thought Faithfulness of Large (Vision) Language Models

   Publicado: 5/6/2025
4. Simplifying Bayesian Optimization Via In-Context Direct Optimum Sampling

   Publicado: 5/6/2025
5. Bayesian Teaching Enables Probabilistic Reasoning in Large Language Models

   Publicado: 5/6/2025
6. IPO: Interpretable Prompt Optimization for Vision-Language Models

   Publicado: 5/6/2025
7. Evolutionary Prompt Optimization discovers emergent multimodal reasoning strategies

   Publicado: 5/6/2025
8. Evaluating the Unseen Capabilities: How Many Theorems Do LLMs Know?

   Publicado: 4/6/2025
9. Diffusion Guidance Is a Controllable Policy Improvement Operator

   Publicado: 2/6/2025
10. Alita: Generalist Agent With Self-Evolution

    Publicado: 2/6/2025
11. A Snapshot of Influence: A Local Data Attribution Framework for Online Reinforcement Learning

    Publicado: 2/6/2025
12. Learning Compositional Functions with Transformers from Easy-to-Hard Data

    Publicado: 2/6/2025
13. Preference Learning with Response Time

    Publicado: 2/6/2025
14. Accelerating RL for LLM Reasoning with Optimal Advantage Regression

    Publicado: 31/5/2025
15. Algorithms for reliable decision-making need causal reasoning

    Publicado: 31/5/2025
16. Belief Attribution as Mental Explanation: The Role of Accuracy, Informativity, and Causality

    Publicado: 31/5/2025
17. Distances for Markov chains from sample streams

    Publicado: 31/5/2025
18. When and Why LLMs Fail to Reason Globally

    Publicado: 31/5/2025
19. IDA-Bench: Evaluating LLMs on Interactive Guided Data Analysis

    Publicado: 31/5/2025
20. No Free Lunch: Non-Asymptotic Analysis of Prediction-Powered Inference

    Publicado: 31/5/2025