AI RESEARCH

InstructMoLE: Instruction-Guided Mixture of Low-rank Experts for Multi-Conditional Image Generation

arXiv CS.CV

ArXi:2512.21788v3 Announce Type: replace Parameter-Efficient Fine-Tuning of Diffusion Transformers (DiTs) for diverse, multi-conditional tasks often suffers from task interference when using monolithic adapters like LoRA. The Mixture of Low-rank Experts (MoLE) architecture offers a modular solution, but its potential is usually limited by routing policies that operate at a token level. Such local routing can conflict with the global nature of user instructions, leading to artifacts like spatial fragmentation and semantic drift in complex image generation tasks.