From the 1 of 5 linked papers with an AI index.
5 papers
Do AI Agents Know When a Task Is Simple? Toward Complexity-Aware Reasoning and Execution
Junjie Yin, Xinyu Feng
The paper introduces a method (E3) for large language model agents to estimate task difficulty and execute only the minimal necessary steps, reducing redundant computation when edi…
Tmax: A simple recipe for terminal agents
Hamish Ivison, Junjie Oscar Yin, Rulin Shao +3
Terminal-using agents have quickly become the most popular downstream application of language models (LMs). Despite their prevalence, relatively little academic work has examined R…
Learning to Detect Language Model Training Data via Active Reconstruction
Junjie Oscar Yin, John X. Morris, Vitaly Shmatikov +2
Detecting LLM training data is generally framed as a membership inference attack (MIA) problem. However, conventional MIAs operate passively on fixed model weights, using log-likel…
Approximating Language Model Training Data from Weights
John X. Morris, Junjie Oscar Yin, Woojeong Kim +2
Modern language models often have open weights but closed training data. We formalize the problem of data approximation from model weights and propose several baselines and metrics…
Compute-Constrained Data Selection
Junjie Oscar Yin, Alexander M. Rush
Data selection can reduce the amount of training data needed to finetune LLMs; however, the efficacy of data selection scales directly with its compute. Motivated by the practical…