#machine learning
Mar 2026
Less Data, Faster Convergence: Goal-Driven Data Optimization for Multimodal Instruction Tuning
Goal-Driven Data Optimization (GDO) is presented, a framework that computes six sample descriptors for each candidate and constructs optimized 1$\times$ training subsets for different goals that enables faster convergence with fewer training samples under a fixed training protocol.
Ru-Jie Wu, Haozhe Zhao, Hai Ci et al.
· arXiv.org · 0 citations