Best AI papers explained

150 Episodes

1. Getting More Juice Out of the SFT Data: Reward Learning from Human Demonstration Improves SFT

   Published: 5/2/2025
2. Self-Consuming Generative Models with Curated Data

   Published: 5/2/2025
3. Bootstrapping Language Models with DPO Implicit Rewards

   Published: 5/2/2025
4. DeepSeek-Prover-V2: Advancing Formal Reasoning

   Published: 5/1/2025
5. THINKPRM: Data-Efficient Process Reward Models

   Published: 5/1/2025
6. Societal Frameworks and LLM Alignment

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

   Published: 4/29/2025
8. Causality-Aware Alignment for Large Language Model Debiasing

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

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

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

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

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

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

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

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

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

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

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

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

    Published: 4/27/2025