Minsik Choi

Decentralized Instruction Tuning: Conflict-Aware Splitting and Weight Merging

Instruction tuning aligns large (multimodal) language models with diverse user intents, but scaling to heterogeneous mixtures is hindered by (i) gradient interference that causes negative transfer and stiff high-curvature dynamics, and (ii) bandwidth-heavy synchronization that is often impractical o…