Best AI papers explained

520 Episoade

1. Interpretable Reward Modeling with Active Concept Bottlenecks

   Publicat: 14.07.2025
2. PrefillOnly: An Inference Engine for Prefill-only Workloads in Large Language Model Applications

   Publicat: 14.07.2025
3. A Collectivist, Economic Perspective on AI

   Publicat: 14.07.2025
4. Textual Bayes: Quantifying Uncertainty in LLM-Based Systems

   Publicat: 12.07.2025
5. The Winner's Curse in Data-Driven Decisions

   Publicat: 11.07.2025
6. SPIRAL: Self-Play for Reasoning Through Zero-Sum Games

   Publicat: 11.07.2025
7. Beyond Statistical Learning: Exact Learning Is Essential for General Intelligence

   Publicat: 11.07.2025
8. Aligning Learning and Endogenous Decision-Making

   Publicat: 11.07.2025
9. Reliable Statistical Inference with Synthetic Data from Large Language Models

   Publicat: 11.07.2025
10. Multi-Turn Reinforcement Learning from Human Preference Feedback

    Publicat: 10.07.2025
11. Provably Learning from Language Feedback

    Publicat: 09.07.2025
12. Markets with Heterogeneous Agents: Dynamics and Survival of Bayesian vs. No-Regret Learners

    Publicat: 05.07.2025
13. Why Neural Network Can Discover Symbolic Structures with Gradient-based Training: An Algebraic and Geometric Foundation

    Publicat: 05.07.2025
14. Causal Abstraction with Lossy Representations

    Publicat: 04.07.2025
15. The Winner's Curse in Data-Driven Decisions

    Publicat: 04.07.2025
16. Embodied AI Agents: Modeling the World

    Publicat: 04.07.2025
17. Beyond Statistical Learning: Exact Learning Is Essential for General Intelligence

    Publicat: 04.07.2025
18. What Has a Foundation Model Found? Inductive Bias Reveals World Models

    Publicat: 04.07.2025
19. Language Bottleneck Models: A Framework for Interpretable Knowledge Tracing and Beyond

    Publicat: 03.07.2025
20. Learning to Explore: An In-Context Learning Approach for Pure Exploration

    Publicat: 03.07.2025