AI RESEARCH
SOLAR: Communication-Efficient Model Adaptation via Subspace-Oriented Latent Adapter Reparametrization
arXiv CS.CL
•
ArXi:2604.08368v1 Announce Type: cross Parameter-efficient fine-tuning (PEFT) methods, such as LoRA, enable scalable adaptation of foundation models by injecting low-rank adapters. However, their communication and storage costs remain a major bottleneck in resource-constrained settings. We propose SOLAR (Subspace-Oriented Latent Adapter Reparameterization), a post-