3 papers
cs.LG2026
M-Loss: Quantifying Model Merging Compatibility with Limited Unlabeled Data
Tiantong Wang, Yiyang Duan, Haoyu Chen +2
Training of large-scale models is both computationally intensive and often constrained by the availability of labeled data. Model merging offers a compelling alternative by directl…
hep-ex2025
New Measurements of the Deuteron to Proton F2 Structure Function Ratio
Debaditya Biswas, Fernando Araiza Gonzalez, William Henry +89
Nucleon structure functions, as measured in lepton-nucleon scattering, have historically provided a critical observable in the study of partonic dynamics within the nucleon. Howeve…
cs.SE2025
Automatically Generating Rules of Malicious Software Packages via Large Language Model
XiangRui Zhang, HaoYu Chen, Yongzhong He +2
Today's security tools predominantly rely on predefined rules crafted by experts, making them poorly adapted to the emergence of software supply chain attacks. To tackle this limit…