Best AI papers explained

456 Episodes

1. Agentic Supernet for Multi-agent Architecture Search

   Published: 6/11/2025
2. Sample Complexity and Representation Ability of Test-time Scaling Paradigms

   Published: 6/11/2025
3. Aligning with Human Judgement: The Role of Pairwise Preference in Large Language Model Evaluators

   Published: 6/10/2025
4. LLMs Get Lost In Multi-Turn Conversation

   Published: 6/9/2025
5. PromptPex: Automatic Test Generation for Prompts

   Published: 6/8/2025
6. General Agents Need World Models

   Published: 6/8/2025
7. The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models

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

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

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

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

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

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

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

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

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

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

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

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

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

    Published: 6/5/2025