8 papers
World of SWECraft: Agent Collaboration at Scale via Simulated Software Worlds
Shannon Zejiang Shen, Yapei Chang, Qiyao Liang +13
As teams of AI agents take on larger projects and long-standing open problems, agent collaboration offers another dimension for scaling inference-time compute. To understand what m…
Do AI Agents Know When a Task Is Simple? Toward Complexity-Aware Reasoning and Execution
Junjie Yin, Xinyu Feng
Large language model (LLM) agents increasingly automate multi-step engineering and informatics workflows, yet they rarely ask how much effort a task actually requires. They often f…
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…
Lite-SAM Is Actually What You Need for Segment Everything
Jianhai Fu, Yuanjie Yu, Ningchuan Li +5
This paper introduces Lite-SAM, an efficient end-to-end solution for the SegEvery task designed to reduce computational costs and redundancy. Lite-SAM is composed of four main comp…
ModuLoRA: Finetuning 2-Bit LLMs on Consumer GPUs by Integrating with Modular Quantizers
Junjie Yin, Jiahao Dong, Yingheng Wang +2
We propose a memory-efficient finetuning algorithm for large language models (LLMs) that supports finetuning LLMs with 65B parameters in 2/3/4-bit precision on as little as one 24G…