Best AI papers explained

484 Episodes

1. ParaPO: Reducing Language Model Verbatim Reproduction

   Published: 4/26/2025
2. Test-Time RL: Self-Evolving LLMs via Majority Voting Rewards

   Published: 4/25/2025
3. Tina: Tiny LoRA Reasoning Models

   Published: 4/25/2025
4. Evaluating large language models in theory of mind tasks

   Published: 4/25/2025
5. QUEST: Quality Sampling for Machine Translation

   Published: 4/24/2025
6. Offline Preference Learning via Simulated Trajectory Feedback

   Published: 4/24/2025
7. Reasoning Elicitation in Language Models via Counterfactual Feedback

   Published: 4/24/2025
8. Eliciting Human Preferences with Language Models

   Published: 4/24/2025
9. Sub-Optimal Data for Human-in-the-Loop Reinforcement Learning

   Published: 4/24/2025
10. γ-Bench: Evaluating LLMs in Multi-Agent Games

    Published: 4/24/2025
11. DRAFT: Self-Driven LLM Tool Mastery via Documentation Refinement

    Published: 4/24/2025
12. Optimal Prediction Sets for Enhanced Human-AI Accuracy

    Published: 4/24/2025
13. Self-Correction via Reinforcement Learning for Language Models

    Published: 4/24/2025
14. Tractable Multi-Agent Reinforcement Learning through Behavioral Economics

    Published: 4/24/2025
15. Trust or Escalate: LLM Judges with Provable Guarantees for Human Agreement

    Published: 4/24/2025
16. Iterative Nash Policy Optimization for Language Model Alignment

    Published: 4/24/2025
17. SycEval: Benchmarking LLM Sycophancy in Mathematics and Medicine

    Published: 4/23/2025
18. Stack AI: Democratizing Enterprise AI Development

    Published: 4/22/2025
19. Evaluating Modern Recommender Systems: Challenges and Future Directions

    Published: 4/22/2025
20. AI in the Enterprise: Seven Lessons from Frontier Companies by OpenAI

    Published: 4/22/2025