3 papers
cs.LG2026
TIER-MoE: Trust-Informed Expert Routing via Conditional Modality Risk for Multimodal Fusion in Biomedical Classification
Yu Chang, Anzhe Cheng, Chenwei Wu +7
The paper proposes TIER-MoE, a risk‑guided mixture‑of‑experts framework that routes multimodal biomedical data to specialized experts based on estimated modality reliability, impro…
cs.CV2026
ERMoE: Eigen-Reparameterized Mixture-of-Experts for Stable Routing and Interpretable Specialization
Anzhe Cheng, Shukai Duan, Shixuan Li +8
Mixture-of-Experts (MoE) architectures expand model capacity by sparsely activating experts but face two core challenges: misalignment between router logits and each expert's inter…
cs.LG2026
EMoE: Eigenbasis-Guided Routing for Mixture-of-Experts
Anzhe Cheng, Shukai Duan, Shixuan Li +5
The relentless scaling of deep learning models has led to unsustainable computational demands, positioning Mixture-of-Experts (MoE) architectures as a promising path towards greate…