Best AI papers explained

481 Episodes

1. Emergent Strategic AI Equilibrium from Pre-trained Reasoning

   Published: 5/7/2025
2. Benefiting from Proprietary Data with Siloed Training

   Published: 5/6/2025
3. Advantage Alignment Algorithms

   Published: 5/6/2025
4. Asymptotic Safety Guarantees Based On Scalable Oversight

   Published: 5/6/2025
5. What Makes a Reward Model a Good Teacher? An Optimization Perspective

   Published: 5/6/2025
6. Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems

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

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

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

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

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

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

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

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

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

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

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

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

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

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

    Published: 4/28/2025