DPA-MoE: A Runtime Precision Control Framework for MoE Inference
Jaeyun Kim*, Hoonki Lee*, Susie Shin, Hyunmin Kim, Dahyun Lee, Sangyeob Kim†
Allocates precision across routed experts at runtime, so one MoE checkpoint covers a range of weight-size–quality trade-offs without retraining. To appear in Findings of EMNLP 2026.