Best AI papers explained

440 Episodo

1. Semantic Operators: A Declarative Model for Rich, AI-based Data Processing

   Publicado: 22/5/2025
2. Isolated Causal Effects of Language

   Publicado: 22/5/2025
3. Sleep-time Compute: Beyond Inference Scaling at Test-time

   Publicado: 22/5/2025
4. J1: Incentivizing Thinking in LLM-as-a-Judge

   Publicado: 22/5/2025
5. ShiQ: Bringing back Bellman to LLMs

   Publicado: 22/5/2025
6. Policy Learning with a Natural Language Action Space: A Causal Approach

   Publicado: 22/5/2025
7. Multi-Objective Preference Optimization: Improving Human Alignment of Generative Models

   Publicado: 22/5/2025
8. End-to-End Learning for Stochastic Optimization: A Bayesian Perspective

   Publicado: 21/5/2025
9. TEXTGRAD: Automatic Differentiation via Text

   Publicado: 21/5/2025
10. Steering off Course: Reliability Challenges in Steering Language Models

    Publicado: 20/5/2025
11. Past-Token Prediction for Long-Context Robot Policies

    Publicado: 20/5/2025
12. Recovering Coherent Event Probabilities from LLM Embeddings

    Publicado: 20/5/2025
13. Systematic Meta-Abilities Alignment in Large Reasoning Models

    Publicado: 20/5/2025
14. Predictability Shapes Adaptation: An Evolutionary Perspective on Modes of Learning in Transformers

    Publicado: 20/5/2025
15. Efficient Exploration for LLMs

    Publicado: 19/5/2025
16. Rankers, Judges, and Assistants: Towards Understanding the Interplay of LLMs in Information Retrieval Evaluation

    Publicado: 18/5/2025
17. Bayesian Concept Bottlenecks with LLM Priors

    Publicado: 17/5/2025
18. Transformers for In-Context Reinforcement Learning

    Publicado: 17/5/2025
19. Evaluating Large Language Models Across the Lifecycle

    Publicado: 17/5/2025
20. Active Ranking from Human Feedback with DopeWolfe

    Publicado: 16/5/2025