3 papers
cs.LG2025
MoLAN: A Unified Modality-Aware Noise Dynamic Editing Framework for Multimodal Sentiment Analysis
Xingle Xu, Yongkang Liu, Dexian Cai +4
Multimodal Sentiment Analysis aims to integrate information from various modalities, such as audio, visual, and text, to make complementary predictions. However, it often struggles…
cs.LG2025
Why Do More Experts Fail? A Theoretical Analysis of Model Merging
Zijing Wang, Xingle Xu, Yongkang Liu +6
Model merging dramatically reduces storage and computational resources by combining multiple expert models into a single multi-task model. Although recent model merging methods hav…
cs.LG2025
Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning
Yongkang Liu, Xingle Xu, Ercong Nie +5
Parameter-Efficient Fine-Tuning (PEFT) methods achieve performance comparable to Full Fine-Tuning (FFT) while requiring significantly fewer computing resources, making it the go-to…