4 papers
Signature-Guided Capacity Occupancy for Dense Expert Merging
Lingching Tung, Chi-Jui Kim, Beicheng Xu +2
Dense expert merging combines domain-specialized language models into one single checkpoint, typically by admitting task-vector support in weight space. However, this admission is…
MFTune: An Efficient Multi-fidelity Framework for Spark SQL Configuration Tuning
Beicheng Xu, Lingching Tung, Yuchen Wang +2
Apache Spark SQL is a cornerstone of modern big data analytics.However,optimizing Spark SQL performance is challenging due to its vast configuration space and the prohibitive cost…
ChainSWE: Benchmarking Coding Agents on Multi-Bug Software Maintenance
Qirui Jin, Lingching Tung, Kenan Li +13
Language model (LM) agents are increasingly deployed to maintain codebases over extended periods, fixing streams of related defects while carrying context from one fix to the next.…
Tree-Structured Synergy of Large Language Models and Bayesian Optimization for Efficient CASH
Beicheng Xu, Weitong Qian, Lingching Tung +2
To lower the expertise barrier in machine learning, the AutoML community has focused on the CASH problem, which jointly automates algorithm selection and hyperparameter tuning. Whi…