LLaVA-MoLE: Sparse Mixture of LoRA Experts for Mitigating Data Conflicts in Instruction Finetuning MLLMs

Documenti analoghi

• LD-MoLE: Learnable Dynamic Routing for Mixture of LoRA Experts
  di: Zhuang, Yuan, et al.
  Pubblicazione: (2025)
• MoE-LLaVA: Mixture of Experts for Large Vision-Language Models
  di: Lin, Bin, et al.
  Pubblicazione: (2024)
• LLaVA-MoD: Making LLaVA Tiny via MoE Knowledge Distillation
  di: Shu, Fangxun, et al.
  Pubblicazione: (2024)
• MoLE: Enhancing Human-centric Text-to-image Diffusion via Mixture of Low-rank Experts
  di: Zhu, Jie, et al.
  Pubblicazione: (2024)
• TAS-LoRA: Transformer Architecture Search with Mixture-of-LoRA Experts
  di: Jeon, Jeimin, et al.
  Pubblicazione: (2026)