Best AI papers explained

550 Episodes

1. The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models

   Published: 6/7/2025
2. Decisions With Algorithms

   Published: 6/7/2025
3. Adapting, fast and slow: Causal Approach to Few-Shot Sequence Learning

   Published: 6/6/2025
4. Conformal Arbitrage for LLM Objective Balancing

   Published: 6/6/2025
5. Simulation-Based Inference for Adaptive Experiments

   Published: 6/6/2025
6. Agents as Tool-Use Decision-Makers

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

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

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

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

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

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

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

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

    Published: 6/5/2025
15. Evolutionary Prompt Optimization discovers emergent multimodal reasoning strategies

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

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

    Published: 6/2/2025
18. Alita: Generalist Agent With Self-Evolution

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

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

    Published: 6/2/2025