Best AI papers explained

481 Episodes

1. metaTextGrad: Learning to learn with language models as optimizers

   Published: 5/22/2025
2. Semantic Operators: A Declarative Model for Rich, AI-based Data Processing

   Published: 5/22/2025
3. Isolated Causal Effects of Language

   Published: 5/22/2025
4. Sleep-time Compute: Beyond Inference Scaling at Test-time

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

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

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

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

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

   Published: 5/21/2025
10. TEXTGRAD: Automatic Differentiation via Text

    Published: 5/21/2025
11. Steering off Course: Reliability Challenges in Steering Language Models

    Published: 5/20/2025
12. Past-Token Prediction for Long-Context Robot Policies

    Published: 5/20/2025
13. Recovering Coherent Event Probabilities from LLM Embeddings

    Published: 5/20/2025
14. Systematic Meta-Abilities Alignment in Large Reasoning Models

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

    Published: 5/20/2025
16. Efficient Exploration for LLMs

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

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

    Published: 5/17/2025
19. Transformers for In-Context Reinforcement Learning

    Published: 5/17/2025
20. Evaluating Large Language Models Across the Lifecycle

    Published: 5/17/2025