Best AI papers explained

456 Episodes

1. Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems

   Published: 5/6/2025
2. Identifiable Steering via Sparse Autoencoding of Multi-Concept Shifts

   Published: 5/6/2025
3. You Are What You Eat - AI Alignment Requires Understanding How Data Shapes Structure and Generalisation

   Published: 5/6/2025
4. Interplay of LLMs in Information Retrieval Evaluation

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

    Published: 4/27/2025