4 papers
CapVector: Learning Transferable Capability Vectors in Parametric Space for Vision-Language-Action Models
Wenxuan Song, Han Zhao, Fuhao Li +7
This paper proposes a novel approach to address the challenge that pretrained VLA models often fail to effectively improve performance and reduce adaptation costs during standard s…
Revitalizing the Beginning: Avoiding Storage Dependency for Model Merging in Continual Learning
Xi Wang, Cheng Deng
Model merging provides a compelling paradigm for integrating specialized expertise into a unified multi-task model, a goal that aligns naturally with the sequential knowledge acqui…
DIMoE-Adapters: Dynamic Expert Evolution for Continual Learning in Vision-Language Models
Mengxin Qin, Xiang Zhang, Xi Wang +3
Continual learning enables vision-language models to accumulate knowledge and adapt to evolving tasks without retraining from scratch. However, in multi-domain task-incremental lea…
Compensating Visual Insufficiency with Stratified Language Guidance for Long-Tail Class Incremental Learning
Xi Wang, Xu Yang, Donghao Sun +1
Long-tail class incremental learning (LT CIL) remains highly challenging because the scarcity of samples in tail classes not only hampers their learning but also exacerbates catast…