RoDE: Linear Rectified Mixture of Diverse Experts for Food Large Multi-Modal Models

Documenti analoghi

• Don't Deceive Me: Mitigating Gaslighting through Attention Reallocation in LMMs
  di: Jiao, Pengkun, et al.
  Pubblicazione: (2025)
• From Holistic to Localized: Local Enhanced Adapters for Efficient Visual Instruction Fine-Tuning
  di: Jiao, Pengkun, et al.
  Pubblicazione: (2024)
• FoodLMM: A Versatile Food Assistant using Large Multi-modal Model
  di: Yin, Yuehao, et al.
  Pubblicazione: (2023)
• Advancing Food Nutrition Estimation via Visual-Ingredient Feature Fusion
  di: Qi, Huiyan, et al.
  Pubblicazione: (2025)
• Towards Unbiased Cross-Modal Representation Learning for Food Image-to-Recipe Retrieval
  di: Wang, Qing, et al.
  Pubblicazione: (2025)