Best AI papers explained

153 Episodes

1. Interplay of LLMs in Information Retrieval Evaluation

   Published: 5/3/2025
2. Trade-Offs Between Tasks Induced by Capacity Constraints Bound the Scope of Intelligence

   Published: 5/3/2025
3. Toward Efficient Exploration by Large Language Model Agents

   Published: 5/3/2025
4. Getting More Juice Out of the SFT Data: Reward Learning from Human Demonstration Improves SFT

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

    Published: 4/27/2025