AI RESEARCH
Decentralized Instruction Tuning: Conflict-Aware Splitting and Weight Merging
arXiv CS.LG
•
ArXi:2606.01717v1 Announce Type: new Instruction tuning aligns large language models, including multimodal ones, with diverse user intents, but scaling to heterogeneous mixtures is hindered by gradient interference and bandwidth-heavy synchronization. We ask whether these two bottlenecks can be addressed jointly by