Best AI papers explained

481 Episodes

1. RAFT: In-Domain Retrieval-Augmented Fine-Tuning for Language Models

   Published: 3/27/2025
2. Inductive Biases for Exchangeable Sequence Modeling

   Published: 3/26/2025
3. InverseRLignment: LLM Alignment via Inverse Reinforcement Learning

   Published: 3/26/2025
4. Prompt-OIRL: Offline Inverse RL for Query-Dependent Prompting

   Published: 3/26/2025
5. Alignment from Demonstrations for Large Language Models

   Published: 3/25/2025
6. Q♯: Distributional RL for Optimal LLM Post-Training

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

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

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

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

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

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

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

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

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

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

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

    Published: 3/13/2025
18. 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
19. Adaptive elicitation of latent information Using natural language

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

    Published: 3/13/2025