{"ID":6620641,"CreatedAt":"2026-07-15T01:01:48.440468303Z","UpdatedAt":"2026-07-15T03:28:55.185153975Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.12686","arxiv_id":"2607.12686","title":"Segregate, Refine, Integrate: Decomposing Multimodal Fusion for Sentiment Analysis","abstract":"Multimodal fusion must simultaneously refine modality-specific signals and model cross-modal interactions; two competing objectives typically entangled within the same operation. We propose \\textbf{SeRIn} (\\textbf{Se}gregate, \\textbf{R}efine, \\textbf{In}tegrate), a multimodal LM fusion scheme that enforces this separation as an architectural prior. Modality-specific representations evolve along isolated pathways, each refined against its respective encoder context, while a dedicated cross-modal pathway accumulates their joint evolution without contaminating unimodal streams. Full cross-modal interaction is deferred to a final prediction step - ablations confirm that structured interactions, not added capacity, drive the gains; gate analysis under visual corruption reveals emergent modality reweighting without explicit supervision. SeRIn achieves state-of-the-art results on CH-SIMS and CMU-MOSEI, improving all metrics on both benchmarks.","short_abstract":"Multimodal fusion must simultaneously refine modality-specific signals and model cross-modal interactions; two competing objectives typically entangled within the same operation. We propose \\textbf{SeRIn} (\\textbf{Se}gregate, \\textbf{R}efine, \\textbf{In}tegrate), a multimodal LM fusion scheme that enforces this separat...","url_abs":"https://arxiv.org/abs/2607.12686","url_pdf":"https://arxiv.org/pdf/2607.12686v1","authors":"[\"Alexios Filippakopoulos\",\"Elias Kallioras\",\"Nikolaos Xiros\",\"Efthymios Georgiou\",\"Alexandros Potamianos\"]","published":"2026-07-14T12:13:53Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[]","has_code":false}