4 papers
Rethinking Data Curation in LLM Training: Online Reweighting Offers Better Generalization than Offline Methods
Wanru Zhao, Yihong Chen, Yuzhi Tang +6
Data curation is a critical yet under-explored area in large language model (LLM) training. Existing methods, such as data selection and mixing, operate in an offline paradigm, det…
From Misclassifications to Outliers: Joint Reliability Assessment in Classification
Yang Li, Youyang Sha, Yinzhi Wang +4
Building reliable classifiers is a fundamental challenge for deploying machine learning in real-world applications. A reliable system should not only detect out-of-distribution (OO…
FW-Merging: Scaling Model Merging with Frank-Wolfe Optimization
Hao Mark Chen, Shell Xu Hu, Wayne Luk +2
Model merging has emerged as a promising approach for multi-task learning (MTL), offering a data-efficient alternative to conventional fine-tuning. However, with the rapid developm…
MobileQuant: Mobile-friendly Quantization for On-device Language Models
Fuwen Tan, Royson Lee, Åukasz Dudziak +5
Large language models (LLMs) have revolutionized language processing, delivering outstanding results across multiple applications. However, deploying LLMs on edge devices poses sev…