2 papers
cs.CL2026
TEXAS: Task-Expert-Aware Supervision for Downstream Mixture-of-Experts LLM Adaptation
Guanzhi Deng, Haibo Wang, Kuan Wu +5
Mixture-of-Experts (MoE) language models route each token through a small subset of experts, making routing patterns useful for identifying task-relevant experts during downstream…
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…