C3PO: Critical-Layer, Core-Expert, Collaborative Pathway Optimization for Test-Time Expert Re-Mixing

Documenti analoghi

• R2-T2: Re-Routing in Test-Time for Multimodal Mixture-of-Experts
  di: Li, Zhongyang, et al.
  Pubblicazione: (2025)
• Routing Manifold Alignment Improves Generalization of Mixture-of-Experts LLMs
  di: Li, Zhongyang, et al.
  Pubblicazione: (2025)
• Your Mixture-of-Experts LLM Is Secretly an Embedding Model For Free
  di: Li, Ziyue, et al.
  Pubblicazione: (2024)
• Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs
  di: Li, Ziyue, et al.
  Pubblicazione: (2025)
• TimeExpert: Boosting Long Time Series Forecasting with Temporal Mix of Experts
  di: Ma, Xiaowen, et al.
  Pubblicazione: (2025)