Self-Routed Tensor Adapters for Parameter-Efficient Universal Visual Adaptation

Excerpt

arXiv:2608.16384v1 Announce Type: cross Abstract: Universal visual representations require adaptation mechanisms that adapt across heterogeneous domains without fragmenting knowledge into domain-specific modules. Parameter-efficient fine-tuning adapts frozen visual foundation models efficiently, but standard low-rank adapters use a fixed subspace for all inputs, which can be restrictive when domains differ in style, background, and semantic context. MoE-based adapters improve specialization thro