Best AI papers explained

442 Episodo

1. Reward Models Evaluate Consistency, Not Causality

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

    Publicado: 26/4/2025
18. LoRe: Low-Rank Reward Modeling for Personalized LLMs

    Publicado: 26/4/2025
19. ParaPO: Reducing Language Model Verbatim Reproduction

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

    Publicado: 25/4/2025