Best AI papers explained

520 Odcinki

1. A Closer Look at Bias and Chain-of-Thought Faithfulness of Large (Vision) Language Models

   Opublikowany: 5.06.2025
2. Simplifying Bayesian Optimization Via In-Context Direct Optimum Sampling

   Opublikowany: 5.06.2025
3. Bayesian Teaching Enables Probabilistic Reasoning in Large Language Models

   Opublikowany: 5.06.2025
4. IPO: Interpretable Prompt Optimization for Vision-Language Models

   Opublikowany: 5.06.2025
5. Evolutionary Prompt Optimization discovers emergent multimodal reasoning strategies

   Opublikowany: 5.06.2025
6. Evaluating the Unseen Capabilities: How Many Theorems Do LLMs Know?

   Opublikowany: 4.06.2025
7. Diffusion Guidance Is a Controllable Policy Improvement Operator

   Opublikowany: 2.06.2025
8. Alita: Generalist Agent With Self-Evolution

   Opublikowany: 2.06.2025
9. A Snapshot of Influence: A Local Data Attribution Framework for Online Reinforcement Learning

   Opublikowany: 2.06.2025
10. Learning Compositional Functions with Transformers from Easy-to-Hard Data

    Opublikowany: 2.06.2025
11. Preference Learning with Response Time

    Opublikowany: 2.06.2025
12. Accelerating RL for LLM Reasoning with Optimal Advantage Regression

    Opublikowany: 31.05.2025
13. Algorithms for reliable decision-making need causal reasoning

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

    Opublikowany: 31.05.2025
15. Distances for Markov chains from sample streams

    Opublikowany: 31.05.2025
16. When and Why LLMs Fail to Reason Globally

    Opublikowany: 31.05.2025
17. IDA-Bench: Evaluating LLMs on Interactive Guided Data Analysis

    Opublikowany: 31.05.2025
18. No Free Lunch: Non-Asymptotic Analysis of Prediction-Powered Inference

    Opublikowany: 31.05.2025
19. Accelerating RL for LLM Reasoning with Optimal Advantage Regression

    Opublikowany: 31.05.2025
20. Statistical Inference for Online Algorithms

    Opublikowany: 31.05.2025