Best AI papers explained

525 Episodes

1. Agents as Tool-Use Decision-Makers

   Published: 6/06/2025
2. Quantitative Judges for Large Language Models

   Published: 6/06/2025
3. Self-Challenging Language Model Agents

   Published: 6/06/2025
4. Learning to Explore: An In-Context Learning Approach for Pure Exploration

   Published: 6/06/2025
5. How Bidirectionality Helps Language Models Learn Better via Dynamic Bottleneck Estimation

   Published: 6/06/2025
6. A Closer Look at Bias and Chain-of-Thought Faithfulness of Large (Vision) Language Models

   Published: 5/06/2025
7. Simplifying Bayesian Optimization Via In-Context Direct Optimum Sampling

   Published: 5/06/2025
8. Bayesian Teaching Enables Probabilistic Reasoning in Large Language Models

   Published: 5/06/2025
9. IPO: Interpretable Prompt Optimization for Vision-Language Models

   Published: 5/06/2025
10. Evolutionary Prompt Optimization discovers emergent multimodal reasoning strategies

    Published: 5/06/2025
11. Evaluating the Unseen Capabilities: How Many Theorems Do LLMs Know?

    Published: 4/06/2025
12. Diffusion Guidance Is a Controllable Policy Improvement Operator

    Published: 2/06/2025
13. Alita: Generalist Agent With Self-Evolution

    Published: 2/06/2025
14. A Snapshot of Influence: A Local Data Attribution Framework for Online Reinforcement Learning

    Published: 2/06/2025
15. Learning Compositional Functions with Transformers from Easy-to-Hard Data

    Published: 2/06/2025
16. Preference Learning with Response Time

    Published: 2/06/2025
17. Accelerating RL for LLM Reasoning with Optimal Advantage Regression

    Published: 31/05/2025
18. Algorithms for reliable decision-making need causal reasoning

    Published: 31/05/2025
19. Belief Attribution as Mental Explanation: The Role of Accuracy, Informativity, and Causality

    Published: 31/05/2025
20. Distances for Markov chains from sample streams

    Published: 31/05/2025