Best AI papers explained

203 Episoder

1. Epistemic Alignment in User-LLM Knowledge Delivery

   Publisert: 6.4.2025
2. MCP is (not) all you need

   Publisert: 6.4.2025
3. AI, Human Skills, and Competitive Advantage in Chess

   Publisert: 5.4.2025
4. Inference-Time Scaling for Generalist Reward Modeling

   Publisert: 4.4.2025
5. Optimal Pure Exploration in Linear Bandits via Sampling

   Publisert: 4.4.2025
6. Presidential Address: The Economist as Designer in the Innovation Process for Socially Impactful Digital Products

   Publisert: 4.4.2025
7. Emergent Symbolic Mechanisms for Reasoning in Large Language Models

   Publisert: 3.4.2025
8. Inference-Time Alignment: Coverage, Scaling, and Optimality

   Publisert: 3.4.2025
9. Sharpe Ratio-Guided Active Learning for Preference Optimization

   Publisert: 3.4.2025
10. Active Learning for Adaptive In-Context Prompt Design

    Publisert: 3.4.2025
11. Visual Chain-of-Thought Reasoning for Vision-Language-Action Models

    Publisert: 3.4.2025
12. On the Biology of a Large Language Model

    Publisert: 1.4.2025
13. Async-TB: Asynchronous Trajectory Balance for Scalable LLM RL

    Publisert: 1.4.2025
14. Instacart's Economics Team: A Hybrid Role in Tech

    Publisert: 31.3.2025
15. Data Mixture Optimization: A Multi-fidelity Multi-scale Bayesian Framework

    Publisert: 31.3.2025
16. Why MCP won

    Publisert: 31.3.2025
17. SWEET-RL: Training LLM Agents for Collaborative Reasoning

    Publisert: 31.3.2025
18. TheoryCoder: Bilevel Planning with Synthesized World Models

    Publisert: 30.3.2025
19. Driving Forces in AI: Scaling to 2025 and Beyond (Jason Wei, OpenAI)

    Publisert: 29.3.2025
20. Expert Demonstrations for Sequential Decision Making under Heterogeneity

    Publisert: 28.3.2025