Input Domain Aware MoE: Decoupling Routing Decisions from Task Optimization in Mixture of Experts

Documenti analoghi

• TAG-MoE: Task-Aware Gating for Unified Generative Mixture-of-Experts
  di: Xu, Yu, et al.
  Pubblicazione: (2026)
• DiG: Differential Grounding for Enhancing Fine-Grained Perception in Multimodal Large Language Model
  di: Tao, Zhou, et al.
  Pubblicazione: (2025)
• Harder Tasks Need More Experts: Dynamic Routing in MoE Models
  di: Huang, Quzhe, et al.
  Pubblicazione: (2024)
• BLR-MoE: Boosted Language-Routing Mixture of Experts for Domain-Robust Multilingual E2E ASR
  di: Ma, Guodong, et al.
  Pubblicazione: (2025)
• CARL-MoE: Communication-Aware Adaptive Routing with Load-Balanced Expert Parallelism for Efficient Mixture-of-Experts Training
  di: Jin, Haopeng
  Pubblicazione: (2026)