← Search

Xiangjin Xie

2 accepted papers

2025

Frozen Language Models Are Gradient Coherence Rectifiers in Vision Transformers

AAAI 2025technical

Large language models (LLMs) have demonstrated remarkable performance in multimodal tasks even with frozen LLM Block and only a few trainable parameters. However, the underlying mechanisms of how LLMs enhance multimodal performance remains unclear. In this work, we focus on the phenomenon that ``Mer…

Cited by 0SourcePDFScholar
2023

Global Mixup: Eliminating Ambiguity with Clustering

AAAI 2023technical

Data augmentation with Mixup has been proven an effective method to regularize the current deep neural networks. Mixup generates virtual samples and corresponding labels simultaneously by linear interpolation. However, the one-stage generation paradigm and the use of linear interpolation have two de…

Cited by 5SourcePDFScholar