Best AI papers explained
Ein Podcast von Enoch H. Kang
518 Folgen
-
Causal Interpretation of Transformer Self-Attention
Vom: 24.5.2025 -
A Causal World Model Underlying Next Token Prediction: Exploring GPT in a Controlled Environment
Vom: 24.5.2025 -
Trace is the Next AutoDiff: Generative Optimization with Rich Feedback, Execution Traces, and LLMs
Vom: 24.5.2025 -
Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation
Vom: 24.5.2025 -
Prompts from Reinforcement Learning (PRL)
Vom: 24.5.2025 -
Logits are All We Need to Adapt Closed Models
Vom: 24.5.2025 -
Large Language Models Are (Bayesian) Latent Variable Models: Explaining and Finding Good Demonstrations for In-Context Learning
Vom: 23.5.2025 -
Inference-Time Intervention: Eliciting Truthful Answers from a Language Model
Vom: 23.5.2025 -
From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models
Vom: 23.5.2025 -
LLM In-Context Learning as Kernel Regression
Vom: 23.5.2025 -
Personalizing LLMs via Decode-Time Human Preference Optimization
Vom: 23.5.2025 -
Almost Surely Safe LLM Inference-Time Alignment
Vom: 23.5.2025 -
Survey of In-Context Learning Interpretation and Analysis
Vom: 23.5.2025 -
From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models
Vom: 23.5.2025 -
LLM In-Context Learning as Kernel Regression
Vom: 23.5.2025 -
Where does In-context Learning Happen in Large Language Models?
Vom: 23.5.2025 -
Auto-Differentiating Any LLM Workflow: A Farewell to Manual Prompting
Vom: 22.5.2025 -
metaTextGrad: Learning to learn with language models as optimizers
Vom: 22.5.2025 -
Semantic Operators: A Declarative Model for Rich, AI-based Data Processing
Vom: 22.5.2025 -
Isolated Causal Effects of Language
Vom: 22.5.2025
Cut through the noise. We curate and break down the most important AI papers so you don’t have to.
