Keeping Yourself is Important in Downstream Tuning Multimodal Large Language Model

Documenti analoghi

• Learn from Downstream and Be Yourself in Multimodal Large Language Model Fine-Tuning
  di: Huang, Wenke, et al.
  Pubblicazione: (2024)
• ThanoRA: Task Heterogeneity-Aware Multi-Task Low-Rank Adaptation
  di: Liang, Jian, et al.
  Pubblicazione: (2025)
• LoRASculpt: Sculpting LoRA for Harmonizing General and Specialized Knowledge in Multimodal Large Language Models
  di: Liang, Jian, et al.
  Pubblicazione: (2025)
• MAPO: Mixed Advantage Policy Optimization
  di: Huang, Wenke, et al.
  Pubblicazione: (2025)
• SafeGRPO: Self-Rewarded Multimodal Safety Alignment via Rule-Governed Policy Optimization
  di: Rong, Xuankun, et al.
  Pubblicazione: (2025)