Best AI papers explained

481 Episodes

1. The Parallel Knowledge Gradient Method for Batch Bayesian Optimization

   Published: 5/24/2025
2. FunBO: Discovering Acquisition Functions for Bayesian Optimization with FunSearch

   Published: 5/24/2025
3. Automated Social Science: A Structural Causal Model-Based Approach

   Published: 5/24/2025
4. Causal Interpretation of Transformer Self-Attention

   Published: 5/24/2025
5. A Causal World Model Underlying Next Token Prediction: Exploring GPT in a Controlled Environment

   Published: 5/24/2025
6. Trace is the Next AutoDiff: Generative Optimization with Rich Feedback, Execution Traces, and LLMs

   Published: 5/24/2025
7. Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation

   Published: 5/24/2025
8. Prompts from Reinforcement Learning (PRL)

   Published: 5/24/2025
9. Logits are All We Need to Adapt Closed Models

   Published: 5/24/2025
10. Large Language Models Are (Bayesian) Latent Variable Models: Explaining and Finding Good Demonstrations for In-Context Learning

    Published: 5/23/2025
11. Inference-Time Intervention: Eliciting Truthful Answers from a Language Model

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

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

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

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

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

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

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

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

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

    Published: 5/22/2025