Best AI papers explained

550 Episodes

1. DoubleGen - Debiased Generative Modeling of Counterfactuals

   Published: 9/27/2025
2. What Characterizes Effective Reasoning? Revisiting Length, Review, and Structure of CoT

   Published: 9/27/2025
3. Compute as Teacher: Turning Inference Compute Into Reference-Free Supervision

   Published: 9/27/2025
4. Learning without training: The implicit dynamics of in-context learning

   Published: 9/24/2025
5. Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model

   Published: 9/24/2025
6. Open Problems in Mechanistic Interpretability

   Published: 9/21/2025
7. Maestro: Joint Graph & Config Optimization for Reliable AI Agents

   Published: 9/21/2025
8. Thought Anchors: Which LLM Reasoning Steps Matter?

   Published: 9/21/2025
9. Sample Complexity and Representation Ability of Test-time Scaling Paradigms

   Published: 9/9/2025
10. RL's Razor: Why Online RL Forgets Less

    Published: 9/7/2025
11. Why Language Models Hallucinate

    Published: 9/6/2025
12. ALFA: Aligning LLMs to Ask Good Questions A Case Study in Clinical Reasoning

    Published: 9/6/2025
13. Sample Efficient Preference Alignment in LLMs via Active Exploration

    Published: 9/6/2025
14. Adventures in Demand Analysis Using AI

    Published: 9/4/2025
15. Memento: Fine-tuning LLM Agents without Fine-tuning LLMs

    Published: 9/1/2025
16. On the Theoretical Limitations of Embedding-Based Retrieval

    Published: 8/31/2025
17. Performance Prediction for Large Systems via Text-to-Text Regression

    Published: 8/30/2025
18. Demystifying the Visual Quality Paradox in Multimodal Large Language Models

    Published: 8/30/2025
19. Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL

    Published: 8/30/2025
20. Compute-Optimal Scaling for Value-Based Deep RL

    Published: 8/25/2025