Best AI papers explained

527 Episodes

1. DeepSeek-Prover-V2: Advancing Formal Reasoning

   Published: 1/05/2025
2. THINKPRM: Data-Efficient Process Reward Models

   Published: 1/05/2025
3. Societal Frameworks and LLM Alignment

   Published: 29/04/2025
4. Risks from Multi-Agent Advanced AI

   Published: 29/04/2025
5. Causality-Aware Alignment for Large Language Model Debiasing

   Published: 29/04/2025
6. Reward Models Evaluate Consistency, Not Causality

   Published: 28/04/2025
7. Causal Rewards for Large Language Model Alignment

   Published: 28/04/2025
8. Sycophancy to subterfuge: Investigating reward-tampering in large language models

   Published: 28/04/2025
9. Bidirectional AI Alignment

   Published: 28/04/2025
10. Why Do Multi-Agent LLM Systems Fail?

    Published: 27/04/2025
11. LLMs as Greedy Agents: RL Fine-tuning for Decision-Making

    Published: 27/04/2025
12. LLM Feedback Loops and the Lock-in Hypothesis

    Published: 27/04/2025
13. Representational Alignment Drives Effective Teaching and Learning

    Published: 27/04/2025
14. Adaptive Parallel Reasoning with Language Models

    Published: 27/04/2025
15. AI: Rewiring the Flow of Ideas and Human Knowledge

    Published: 27/04/2025
16. Learning and Equilibrium with Ranking Feedback

    Published: 27/04/2025
17. Designing Human-AI Collaboration: A Sufficient-Statistic Approach

    Published: 27/04/2025
18. GOAT: Generative Adversarial Training for Human-AI Coordination

    Published: 27/04/2025
19. π0.5: Generalization in Robotic Manipulation via Diverse Data

    Published: 27/04/2025
20. NoWag: Unified Compression for Large Language Models

    Published: 26/04/2025