Dynamic Self-adaptive Multiscale Distillation from Pre-trained Multimodal Large Model for Efficient Cross-modal Representation Learning

Similar Items

• AIM: Let Any Multi-modal Large Language Models Embrace Efficient In-Context Learning
  by: Gao, Jun, et al.
  Published: (2024)
• Not All Attention is Needed: Parameter and Computation Efficient Transfer Learning for Multi-modal Large Language Models
  by: Wu, Qiong, et al.
  Published: (2024)
• CMATH: Cross-Modality Augmented Transformer with Hierarchical Variational Distillation for Multimodal Emotion Recognition in Conversation
  by: Zhu, Xiaofei, et al.
  Published: (2024)
• Distilling Implicit Multimodal Knowledge into Large Language Models for Zero-Resource Dialogue Generation
  by: Zhang, Bo, et al.
  Published: (2024)
• A Simple Method to Enhance Pre-trained Language Models with Speech Tokens for Classification
  by: Calbucura, Nicolas, et al.
  Published: (2025)