Jul 2026
AlphaWiSE: Adaptive Weight Interpolation for Continual Multimodal Representation Learning
This work proposes AlphaWiSE, a post-hoc weight-space interpolation method that composes two frozen source checkpoints that fits one scalar interpolation coefficient shared by all tensor entries for cross-modal retrieval.
Sarthak Jain, Qi-Ran Hu, Zhen Zhu et al.
· arXiv.org · 0 citations