Best AI papers explained

456 Episodes

1. Q♯: Distributional RL for Optimal LLM Post-Training

   Published: 3/18/2025
2. Scaling Test-Time Compute Without Verification or RL is Suboptimal

   Published: 3/14/2025
3. Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning

   Published: 3/14/2025
4. Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning

   Published: 3/14/2025
5. Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback

   Published: 3/14/2025
6. Revisiting Superficial Alignment Hypothesis

   Published: 3/14/2025
7. Diagnostic uncertainty: teaching language Models to describe open-ended uncertainty

   Published: 3/14/2025
8. Language Model Personalization via Reward Factorization

   Published: 3/14/2025
9. Is a Good Foundation Necessary for Efficient Reinforcement Learning? The Computational Role of the Base Model in Exploration

   Published: 3/14/2025
10. How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach

    Published: 3/14/2025
11. Can Large Language Models Extract Customer Needs as well as Professional Analysts?

    Published: 3/13/2025
12. Spurlens: finding spurious correlations in Multimodal llms

    Published: 3/13/2025
13. Improving test-time search with backtrack- Ing Improving test-time search with backtrack- Ing against in-context value verifiersagainst in-context value verifiers

    Published: 3/13/2025
14. Adaptive elicitation of latent information Using natural language

    Published: 3/13/2025
15. Document Valuation in LLM Summaries: A Cluster Shapley Approach

    Published: 3/13/2025
16. s1: simple test time scaling

    Published: 3/13/2025