Best AI papers explained

442 Episodes

1. Auto-Differentiating Any LLM Workflow: A Farewell to Manual Prompting

   Published: 5/22/2025
2. metaTextGrad: Learning to learn with language models as optimizers

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

    Published: 5/17/2025