Best AI papers explained

437 Episodo

1. IPO: Interpretable Prompt Optimization for Vision-Language Models

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

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

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

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

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

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

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

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

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

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

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

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

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

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

    Publicado: 31/5/2025
16. Accelerating RL for LLM Reasoning with Optimal Advantage Regression

    Publicado: 31/5/2025
17. Statistical Inference for Online Algorithms

    Publicado: 31/5/2025
18. Prismatic Synthesis for Diverse LLM Reasoning Data

    Publicado: 31/5/2025
19. Position: Uncertainty Quantification Needs Reassessment for Large-language Model Agents

    Publicado: 31/5/2025
20. The Agentic Economy

    Publicado: 30/5/2025