InfMasking: Unleashing Synergistic Information by Contrastive Multimodal Interactions

NeurIPSSpotlight2025

Authors: Liangjian Wen, Qun Dai, Jianzhuang Liu, Jiangtao Zheng, Yong Dai, Dongkai Wang, zhao kang, Jun Wang, Zenglin Xu, Jiang Duan
Venue: NeurIPS 2025
Track: Spotlight

TL;DR

In multimodal representation learning, synergistic interactions between modalities not only provide complementary information but also create unique outcomes through specific interaction patterns that…

Opening excerpt from the authors’ abstract. source

Read the paper

OpenReview

Topics

representation learning contrastive multimodal

← All NeurIPS 2025 Spotlight papers · Browse the whole archive