Improving Model Fusion by Training-time Neuron Alignment with Fixed Neuron Anchors

Documenti analoghi

• FedGuCci: Making Local Models More Connected in Landscape for Federated Learning
  di: Li, Zexi, et al.
  Pubblicazione: (2024)
• SafeNeuron: Neuron-Level Safety Alignment for Large Language Models
  di: Wang, Zhaoxin, et al.
  Pubblicazione: (2026)
• Light Alignment Improves LLM Safety via Model Self-Reflection with a Single Neuron
  di: Shen, Sicheng, et al.
  Pubblicazione: (2026)
• Text-to-Model: Text-Conditioned Neural Network Diffusion for Train-Once-for-All Personalization
  di: Li, Zexi, et al.
  Pubblicazione: (2024)
• To 2:4 Sparsity and Beyond: Neuron-level Activation Function to Accelerate LLM Pre-Training
  di: Madhyastha, Meghana, et al.
  Pubblicazione: (2026)