Best AI papers explained
Podcast tekijän mukaan Enoch H. Kang
534 Jaksot
-
Prompts from Reinforcement Learning (PRL)
Julkaistiin: 24.5.2025 -
Logits are All We Need to Adapt Closed Models
Julkaistiin: 24.5.2025 -
Large Language Models Are (Bayesian) Latent Variable Models: Explaining and Finding Good Demonstrations for In-Context Learning
Julkaistiin: 23.5.2025 -
Inference-Time Intervention: Eliciting Truthful Answers from a Language Model
Julkaistiin: 23.5.2025 -
From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models
Julkaistiin: 23.5.2025 -
LLM In-Context Learning as Kernel Regression
Julkaistiin: 23.5.2025 -
Personalizing LLMs via Decode-Time Human Preference Optimization
Julkaistiin: 23.5.2025 -
Almost Surely Safe LLM Inference-Time Alignment
Julkaistiin: 23.5.2025 -
Survey of In-Context Learning Interpretation and Analysis
Julkaistiin: 23.5.2025 -
From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models
Julkaistiin: 23.5.2025 -
LLM In-Context Learning as Kernel Regression
Julkaistiin: 23.5.2025 -
Where does In-context Learning Happen in Large Language Models?
Julkaistiin: 23.5.2025 -
Auto-Differentiating Any LLM Workflow: A Farewell to Manual Prompting
Julkaistiin: 22.5.2025 -
metaTextGrad: Learning to learn with language models as optimizers
Julkaistiin: 22.5.2025 -
Semantic Operators: A Declarative Model for Rich, AI-based Data Processing
Julkaistiin: 22.5.2025 -
Isolated Causal Effects of Language
Julkaistiin: 22.5.2025 -
Sleep-time Compute: Beyond Inference Scaling at Test-time
Julkaistiin: 22.5.2025 -
J1: Incentivizing Thinking in LLM-as-a-Judge
Julkaistiin: 22.5.2025 -
ShiQ: Bringing back Bellman to LLMs
Julkaistiin: 22.5.2025 -
Policy Learning with a Natural Language Action Space: A Causal Approach
Julkaistiin: 22.5.2025
Cut through the noise. We curate and break down the most important AI papers so you don’t have to.
