Research map / Vision-language and multimodal / Cross-modal learning
Disentangled Cross-Modal Representation Learning with Enhanced Mutual Supervision
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes a disentangled multimodal VAE framework for cross-modal representation learning that enhances mutual supervision between modalities to align shared factors and separate modality-specific ones.
Problem
Multimodal VAE-based models for cross-modal representation learning often align heterogeneous modalities poorly or lack structural constraints to separate modality-specific from shared factors.
Approach
A disentangled cross-modal VAE framework with enhanced mutual supervision between modalities to better align shared latent factors while structurally separating modality-specific factors (details beyond the abstract not available).
Closest papers by meaning
- RePercENT: Scaling Disentangled Representation Learning Beyond Two Modalities (NeurIPS 2026 · similarity 0.90)
- An Information Criterion for Controlled Disentanglement of Multimodal Data (ICLR 2025 · similarity 0.90)
- On the Value of Cross-Modal Misalignment in Multimodal Representation Learning (NeurIPS 2025 · similarity 0.89)
- Connect, Collapse, Corrupt: Learning Cross-Modal Tasks with Uni-Modal Data (ICLR 2024 · similarity 0.89)
- RedCore: Relative Advantage Aware Cross-Modal Representation Learning for Missing Modalities with Imbalanced Missing Rates (AAAI 2024 · similarity 0.89)
- Unity by Diversity: Improved Representation Learning for Multimodal VAEs (NeurIPS 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.