AINeutralarXiv – CS AI · 6h ago6/10
🧠
Multi-Modality Distillation via Learning the teacher's modality-level Gram Matrix
Researchers propose a novel knowledge distillation method for multi-modal AI systems that transfers modality relationship information from teacher to student networks by learning the teacher's Gram Matrix. This approach goes beyond existing methods that only focus on final output, enabling deeper knowledge transfer across different data modalities.