Locate-then-Merge: Neuron-Level Parameter Fusion for Mitigating Catastrophic Forgetting in Multimodal LLMs

Documenti analoghi

• Understanding and Mitigating Gender Bias in LLMs via Interpretable Neuron Editing
  di: Yu, Zeping, et al.
  Pubblicazione: (2025)
• Neuron-Level Knowledge Attribution in Large Language Models
  di: Yu, Zeping, et al.
  Pubblicazione: (2023)
• Understanding Multimodal LLMs: the Mechanistic Interpretability of Llava in Visual Question Answering
  di: Yu, Zeping, et al.
  Pubblicazione: (2024)
• Interpreting Arithmetic Mechanism in Large Language Models through Comparative Neuron Analysis
  di: Yu, Zeping, et al.
  Pubblicazione: (2024)
• How do Large Language Models Learn In-Context? Query and Key Matrices of In-Context Heads are Two Towers for Metric Learning
  di: Yu, Zeping, et al.
  Pubblicazione: (2024)