Best AI papers explained

550 Episodes

1. From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models

   Published: 5/23/2025
2. LLM In-Context Learning as Kernel Regression

   Published: 5/23/2025
3. Personalizing LLMs via Decode-Time Human Preference Optimization

   Published: 5/23/2025
4. Almost Surely Safe LLM Inference-Time Alignment

   Published: 5/23/2025
5. Survey of In-Context Learning Interpretation and Analysis

   Published: 5/23/2025
6. From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models

   Published: 5/23/2025
7. LLM In-Context Learning as Kernel Regression

   Published: 5/23/2025
8. Where does In-context Learning Happen in Large Language Models?

   Published: 5/23/2025
9. Auto-Differentiating Any LLM Workflow: A Farewell to Manual Prompting

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

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

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

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

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

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

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

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

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

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

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

    Published: 5/20/2025