MoEEdit: Efficient and Routing-Stable Knowledge Editing for Mixture-of-Experts LLMs

Documenti analoghi

• GRIP: Algorithm-Agnostic Machine Unlearning for Mixture-of-Experts via Geometric Router Constraints
  di: Zhu, Andy, et al.
  Pubblicazione: (2026)
• Sub-MoE: Efficient Mixture-of-Expert LLMs Compression via Subspace Expert Merging
  di: Li, Lujun, et al.
  Pubblicazione: (2025)
• Scalable Knowledge Editing for Mixture-of-Experts LLMs via Tensor-Structured Updates
  di: Maksimov, Roman, et al.
  Pubblicazione: (2026)
• ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing
  di: Wang, Ziteng, et al.
  Pubblicazione: (2024)
• Routing Manifold Alignment Improves Generalization of Mixture-of-Experts LLMs
  di: Li, Zhongyang, et al.
  Pubblicazione: (2025)