Best AI papers explained

525 Episodo

1. Societal Frameworks and LLM Alignment

   Publicado: 29/4/2025
2. Risks from Multi-Agent Advanced AI

   Publicado: 29/4/2025
3. Causality-Aware Alignment for Large Language Model Debiasing

   Publicado: 29/4/2025
4. Reward Models Evaluate Consistency, Not Causality

   Publicado: 28/4/2025
5. Causal Rewards for Large Language Model Alignment

   Publicado: 28/4/2025
6. Sycophancy to subterfuge: Investigating reward-tampering in large language models

   Publicado: 28/4/2025
7. Bidirectional AI Alignment

   Publicado: 28/4/2025
8. Why Do Multi-Agent LLM Systems Fail?

   Publicado: 27/4/2025
9. LLMs as Greedy Agents: RL Fine-tuning for Decision-Making

   Publicado: 27/4/2025
10. LLM Feedback Loops and the Lock-in Hypothesis

    Publicado: 27/4/2025
11. Representational Alignment Drives Effective Teaching and Learning

    Publicado: 27/4/2025
12. Adaptive Parallel Reasoning with Language Models

    Publicado: 27/4/2025
13. AI: Rewiring the Flow of Ideas and Human Knowledge

    Publicado: 27/4/2025
14. Learning and Equilibrium with Ranking Feedback

    Publicado: 27/4/2025
15. Designing Human-AI Collaboration: A Sufficient-Statistic Approach

    Publicado: 27/4/2025
16. GOAT: Generative Adversarial Training for Human-AI Coordination

    Publicado: 27/4/2025
17. π0.5: Generalization in Robotic Manipulation via Diverse Data

    Publicado: 27/4/2025
18. NoWag: Unified Compression for Large Language Models

    Publicado: 26/4/2025
19. Optimal Tool Calls in Language Model Reasoning

    Publicado: 26/4/2025
20. Data Selection for Empirical Risk Minimization

    Publicado: 26/4/2025