Best AI papers explained

440 Episodo

1. FunBO: Discovering Acquisition Functions for Bayesian Optimization with FunSearch

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

   Publicado: 24/5/2025
3. Causal Interpretation of Transformer Self-Attention

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

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

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

   Publicado: 24/5/2025
7. Prompts from Reinforcement Learning (PRL)

   Publicado: 24/5/2025
8. Logits are All We Need to Adapt Closed Models

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

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

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

    Publicado: 23/5/2025
12. LLM In-Context Learning as Kernel Regression

    Publicado: 23/5/2025
13. Personalizing LLMs via Decode-Time Human Preference Optimization

    Publicado: 23/5/2025
14. Almost Surely Safe LLM Inference-Time Alignment

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

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

    Publicado: 23/5/2025
17. LLM In-Context Learning as Kernel Regression

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

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

    Publicado: 22/5/2025
20. metaTextGrad: Learning to learn with language models as optimizers

    Publicado: 22/5/2025