4 papers
EvoGM: Learning to Merge LLMs via Evolutionary Generative Optimization
Tao Jiang, Xinmeng Yu, Chenhao Yi +5
Evolutionary model merging provides a powerful framework for the automated, training-free composition of LLMs through parameter-space search. However, existing methods predominantl…
AlignMamba-2: Enhancing Multimodal Fusion and Sentiment Analysis with Modality-Aware Mamba
Yan Li, Yifei Xing, Xiangyuan Lan +3
In the era of large-scale pre-trained models, effectively adapting general knowledge to specific affective computing tasks remains a challenge, particularly regarding computational…
ARPGNet: Appearance- and Relation-aware Parallel Graph Attention Fusion Network for Facial Expression Recognition
Yan Li, Yong Zhao, Xiaohan Xia +1
The key to facial expression recognition is to learn discriminative spatial-temporal representations that embed facial expression dynamics. Previous studies predominantly rely on p…
AlignMamba: Enhancing Multimodal Mamba with Local and Global Cross-modal Alignment
Yan Li, Yifei Xing, Xiangyuan Lan +3
Cross-modal alignment is crucial for multimodal representation fusion due to the inherent heterogeneity between modalities. While Transformer-based methods have shown promising res…