Best AI papers explained

203 Episoder

1. Test-Time RL: Self-Evolving LLMs via Majority Voting Rewards

   Publisert: 25.4.2025
2. Tina: Tiny LoRA Reasoning Models

   Publisert: 25.4.2025
3. Evaluating large language models in theory of mind tasks

   Publisert: 25.4.2025
4. QUEST: Quality Sampling for Machine Translation

   Publisert: 24.4.2025
5. Offline Preference Learning via Simulated Trajectory Feedback

   Publisert: 24.4.2025
6. Reasoning Elicitation in Language Models via Counterfactual Feedback

   Publisert: 24.4.2025
7. Eliciting Human Preferences with Language Models

   Publisert: 24.4.2025
8. Sub-Optimal Data for Human-in-the-Loop Reinforcement Learning

   Publisert: 24.4.2025
9. γ-Bench: Evaluating LLMs in Multi-Agent Games

   Publisert: 24.4.2025
10. DRAFT: Self-Driven LLM Tool Mastery via Documentation Refinement

    Publisert: 24.4.2025
11. Optimal Prediction Sets for Enhanced Human-AI Accuracy

    Publisert: 24.4.2025
12. Self-Correction via Reinforcement Learning for Language Models

    Publisert: 24.4.2025
13. Tractable Multi-Agent Reinforcement Learning through Behavioral Economics

    Publisert: 24.4.2025
14. Trust or Escalate: LLM Judges with Provable Guarantees for Human Agreement

    Publisert: 24.4.2025
15. Iterative Nash Policy Optimization for Language Model Alignment

    Publisert: 24.4.2025
16. SycEval: Benchmarking LLM Sycophancy in Mathematics and Medicine

    Publisert: 23.4.2025
17. Stack AI: Democratizing Enterprise AI Development

    Publisert: 22.4.2025
18. Evaluating Modern Recommender Systems: Challenges and Future Directions

    Publisert: 22.4.2025
19. AI in the Enterprise: Seven Lessons from Frontier Companies by OpenAI

    Publisert: 22.4.2025
20. Discussion: Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?

    Publisert: 21.4.2025