Best AI papers explained

523 Episoade

1. Self-Challenging Language Model Agents

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

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

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

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

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

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

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

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

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

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

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

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

    Publicat: 02.06.2025
14. Preference Learning with Response Time

    Publicat: 02.06.2025
15. Accelerating RL for LLM Reasoning with Optimal Advantage Regression

    Publicat: 31.05.2025
16. Algorithms for reliable decision-making need causal reasoning

    Publicat: 31.05.2025
17. Belief Attribution as Mental Explanation: The Role of Accuracy, Informativity, and Causality

    Publicat: 31.05.2025
18. Distances for Markov chains from sample streams

    Publicat: 31.05.2025
19. When and Why LLMs Fail to Reason Globally

    Publicat: 31.05.2025
20. IDA-Bench: Evaluating LLMs on Interactive Guided Data Analysis

    Publicat: 31.05.2025