Best AI papers explained

526 Odcinki

1. Data Selection for Empirical Risk Minimization

   Opublikowany: 26.04.2025
2. LoRe: Low-Rank Reward Modeling for Personalized LLMs

   Opublikowany: 26.04.2025
3. ParaPO: Reducing Language Model Verbatim Reproduction

   Opublikowany: 26.04.2025
4. Test-Time RL: Self-Evolving LLMs via Majority Voting Rewards

   Opublikowany: 25.04.2025
5. Tina: Tiny LoRA Reasoning Models

   Opublikowany: 25.04.2025
6. Evaluating large language models in theory of mind tasks

   Opublikowany: 25.04.2025
7. QUEST: Quality Sampling for Machine Translation

   Opublikowany: 24.04.2025
8. Offline Preference Learning via Simulated Trajectory Feedback

   Opublikowany: 24.04.2025
9. Reasoning Elicitation in Language Models via Counterfactual Feedback

   Opublikowany: 24.04.2025
10. Eliciting Human Preferences with Language Models

    Opublikowany: 24.04.2025
11. Sub-Optimal Data for Human-in-the-Loop Reinforcement Learning

    Opublikowany: 24.04.2025
12. γ-Bench: Evaluating LLMs in Multi-Agent Games

    Opublikowany: 24.04.2025
13. DRAFT: Self-Driven LLM Tool Mastery via Documentation Refinement

    Opublikowany: 24.04.2025
14. Optimal Prediction Sets for Enhanced Human-AI Accuracy

    Opublikowany: 24.04.2025
15. Self-Correction via Reinforcement Learning for Language Models

    Opublikowany: 24.04.2025
16. Tractable Multi-Agent Reinforcement Learning through Behavioral Economics

    Opublikowany: 24.04.2025
17. Trust or Escalate: LLM Judges with Provable Guarantees for Human Agreement

    Opublikowany: 24.04.2025
18. Iterative Nash Policy Optimization for Language Model Alignment

    Opublikowany: 24.04.2025
19. SycEval: Benchmarking LLM Sycophancy in Mathematics and Medicine

    Opublikowany: 23.04.2025
20. Stack AI: Democratizing Enterprise AI Development

    Opublikowany: 22.04.2025