SOURCE-LINKED INTELLIGENCE

Hierarchical Wasserstein Merging for Multi-Domain Multi-Task Learning: From Specialists to a Generalist

arXiv · AI, language, vision and robotics · article · Sep 6, 2026 · UTC

Multi-domain multi-task learning (MD-MTL) aims to build a single generalist model that performs well across heterogeneous domains and tasks. However, joint training often suffers from interference under distribution shifts. Existing model merging methods mostly operate on model parameters while overlooking the geometric structure of latent representation distributions across domains and tasks. To address these limitations, we propose Hierarchical Wasserstein Merging (HWM), a representation-level framework that models each domain-task specialist as a distribution of hidden representations on a

Read original source ↗ Open in workspace

recordType

paper

region

Global