STAR rethinks MoE routing as structure-aware subspace learning by adding a GHA-tracked principal subspace to standard routers, yielding more stable specialization and better performance on synthetic, language, and vision tasks.
Sparse mixture-of-experts are domain generalizable learners
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
CrossFlowDG bridges the modality gap in domain generalization by learning a continuous transformation that moves image embeddings to matching text embeddings using noise-free cross-modal flow matching.
LoRA-Mixer routes modular LoRA experts into attention projection matrices with an adaptive Routing Specialization Loss to improve multi-task performance while using fewer trainable parameters than prior LoRA-MoE methods.
citing papers explorer
-
STAR: Rethinking MoE Routing as Structure-Aware Subspace Learning
STAR rethinks MoE routing as structure-aware subspace learning by adding a GHA-tracked principal subspace to standard routers, yielding more stable specialization and better performance on synthetic, language, and vision tasks.
-
CrossFlowDG: Bridging the Modality Gap with Cross-modal Flow Matching for Domain Generalization
CrossFlowDG bridges the modality gap in domain generalization by learning a continuous transformation that moves image embeddings to matching text embeddings using noise-free cross-modal flow matching.
-
LoRA-Mixer: Coordinate Modular LoRA Experts Through Serial Attention Routing
LoRA-Mixer routes modular LoRA experts into attention projection matrices with an adaptive Routing Specialization Loss to improve multi-task performance while using fewer trainable parameters than prior LoRA-MoE methods.