Best AI papers explained

528 Episodes

1. NoWag: Unified Compression for Large Language Models

   Published: 26/04/2025
2. Optimal Tool Calls in Language Model Reasoning

   Published: 26/04/2025
3. Data Selection for Empirical Risk Minimization

   Published: 26/04/2025
4. LoRe: Low-Rank Reward Modeling for Personalized LLMs

   Published: 26/04/2025
5. ParaPO: Reducing Language Model Verbatim Reproduction

   Published: 26/04/2025
6. Test-Time RL: Self-Evolving LLMs via Majority Voting Rewards

   Published: 25/04/2025
7. Tina: Tiny LoRA Reasoning Models

   Published: 25/04/2025
8. Evaluating large language models in theory of mind tasks

   Published: 25/04/2025
9. QUEST: Quality Sampling for Machine Translation

   Published: 24/04/2025
10. Offline Preference Learning via Simulated Trajectory Feedback

    Published: 24/04/2025
11. Reasoning Elicitation in Language Models via Counterfactual Feedback

    Published: 24/04/2025
12. Eliciting Human Preferences with Language Models

    Published: 24/04/2025
13. Sub-Optimal Data for Human-in-the-Loop Reinforcement Learning

    Published: 24/04/2025
14. γ-Bench: Evaluating LLMs in Multi-Agent Games

    Published: 24/04/2025
15. DRAFT: Self-Driven LLM Tool Mastery via Documentation Refinement

    Published: 24/04/2025
16. Optimal Prediction Sets for Enhanced Human-AI Accuracy

    Published: 24/04/2025
17. Self-Correction via Reinforcement Learning for Language Models

    Published: 24/04/2025
18. Tractable Multi-Agent Reinforcement Learning through Behavioral Economics

    Published: 24/04/2025
19. Trust or Escalate: LLM Judges with Provable Guarantees for Human Agreement

    Published: 24/04/2025
20. Iterative Nash Policy Optimization for Language Model Alignment

    Published: 24/04/2025