Research map / Vision-language and multimodal / Cross-modal learning
Mitigating Modality Collapse in Multimodal VAEs via Impartial Optimization
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Apply impartial optimization to the standard VAE | Standard VAE with ELBO · Adult, Credit, Wine, Diamonds, Bank, and IMDB | reconstruction error: Adult: 0.213 -> 0.104; Credit: 0.128 -> 0.041; Wine: 0.086 -> 0.071; Diamonds: 0.187 -> 0.139; Bank: 0.203 -> 0.043; IMD | Helped |
| Apply impartial optimization | MMVAE trained with SIWAE · MNIST-SVHN-Text | reconstruction coherence: MNIST: 58.94593670964241 -> 74.15943145751953; SVHN: 61.26817092299461 -> 68.9321979880333; Text: 63.27350363135338 -> 7 | Helped |
| Apply impartial optimization | Multimodal VAE models · MNIST-SVHN-Text | self and cross generation coherence | Mixed |
| Apply impartial optimization | MVAE, MMVAE, and MoPoE · MNIST-SVHN-Text | cross latent classification accuracy | Helped |
| Apply impartial optimization | Heterogeneous VAE models · Heterogeneous datasets | reconstruction error: 30 out of 36 cases | Mixed |
| Apply impartial optimization | Heterogeneous VAE models · Likelihood types | reconstruction error: Categorical: 0.157897 -> 0.065499; log-normal: 0.064481 -> 0.056633; normal: 0.040884 -> 0.038784; Poisson: 0.058283 -> | Mixed |
Closest papers by meaning
- A Closer Look at Multimodal Representation Collapse (ICML 2025 · similarity 0.91)
- Unity by Diversity: Improved Representation Learning for Multimodal VAEs (NeurIPS 2024 · similarity 0.90)
- Aggregation of Dependent Expert Distributions in Multimodal Variational Autoencoders (ICML 2025 · similarity 0.89)
- Modality-Aware SAM: Sharpness-Aware-Minimization Driven Gradient Modulation for Harmonized Multimodal Learning (NeurIPS 2025 · similarity 0.88)
- Asymmetric Reinforcing Against Multi-Modal Representation Bias (AAAI 2025 · similarity 0.88)
- Beyond Vanilla Variational Autoencoders: Detecting Posterior Collapse in Conditional and Hierarchical Variational Autoencoders (ICLR 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.