Data Science Wire

ExPLoRe: Expert Patch-Level Loss Routing for Multi-Objective Masked Image Modeling

arXiv cs.CV1mo4 min read

arXiv:2606.31201v1 Announce Type: new Abstract: Multi-objective masked image modeling (MIM) combines complementary learning signals (token distillation, CLS alignment, and pixel reconstruction) but existing methods weight these objectives with global scalars, ignoring spatial heterogeneity across patches. We present ExPLoRe (Expert Patch-Level Loss Routing), which repurposes Soft Mixture of Experts (MoE) dispatch weights as learned, per-patch loss coefficients. The key mechanism is loss-coupling: allowing loss gradients to flow through dispatch weights to the router enables content-dependent s

Read the full story at arXiv cs.CV

More in Machine Learning