Best AI papers explained

442 Episodes

1. Reward Models Evaluate Consistency, Not Causality

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

    Published: 4/25/2025