Intent Projection decomposes literal and pragmatic signals in multimodal memes via orthogonal projection and contrastive objectives in LVLMs, outperforming baselines on six benchmarks especially for high-divergence posts.
Yuqi Niu, Dilara Keküllüo˘glu, Weidong Qiu, and Nadin Kokciyan
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Beyond the Literal: Decomposing Pragmatic Intent in Multimodal Meme Understanding
Intent Projection decomposes literal and pragmatic signals in multimodal memes via orthogonal projection and contrastive objectives in LVLMs, outperforming baselines on six benchmarks especially for high-divergence posts.