Cover Image

Can multimodal representation learning by alignment preserve modality-specific information?

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Thoreau, Romain, Levillain, Jessie, Derksen, Dawa
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Parameter-Efficient Adaptation of Geospatial Foundation Models through Embedding Deflection
by: Thoreau, Romain, et al.
Published: (2025)

Closing the gap in multimodal medical representation alignment
by: Grassucci, Eleonora, et al.
Published: (2026)

Tile and Slide : A New Framework for Scaling NeRF from Local to Global 3D Earth Observation
by: Billouard, Camille, et al.
Published: (2025)

Densification and forecasting of Sentinel-2 time series from multimodal SAR and Optical satellite data using deep generative models
by: Defonte, Véronique, et al.
Published: (2026)

AGA: An adaptive group alignment framework for structured medical cross-modal representation learning
by: Li, Wei, et al.
Published: (2025)

What to align in multimodal contrastive learning?
by: Dufumier, Benoit, et al.
Published: (2024)

Buffer replay enhances the robustness of multimodal learning under missing-modality
by: Zhu, Hongye, et al.
Published: (2025)

Model alignment using inter-modal bridges
by: Gholamzadeh, Ali, et al.
Published: (2025)

Toulouse Hyperspectral Data Set: a benchmark data set to assess semi-supervised spectral representation learning and pixel-wise classification techniques
by: Thoreau, Romain, et al.
Published: (2023)

Physics-informed Variational Autoencoders for Improved Robustness to Environmental Factors of Variation
by: Thoreau, Romain, et al.
Published: (2022)

A training regime to learn unified representations from complementary breast imaging modalities
by: Sharma, Umang, et al.
Published: (2024)

Evaluating alignment between humans and neural network representations in image-based learning tasks
by: Demircan, Can, et al.
Published: (2023)

Intrinsic Dimension Correlation: uncovering nonlinear connections in multimodal representations
by: Basile, Lorenzo, et al.
Published: (2024)

Video alignment using unsupervised learning of local and global features
by: Fakhfour, Niloufar, et al.
Published: (2023)

Multi-modal learning for geospatial vegetation forecasting
by: Benson, Vitus, et al.
Published: (2023)

Structure-preserving contrastive learning for spatial time series
by: Jiao, Yiru, et al.
Published: (2025)

SAT-NGP : Unleashing Neural Graphics Primitives for Fast Relightable Transient-Free 3D reconstruction from Satellite Imagery
by: Billouard, Camille, et al.
Published: (2024)

Joint attitude estimation and 3D neural reconstruction of non-cooperative space objects
by: Forray, Clément, et al.
Published: (2025)

Visual representations in the human brain are aligned with large language models
by: Doerig, Adrien, et al.
Published: (2022)

Spectral regularization for adversarially-robust representation learning
by: Yang, Sheng, et al.
Published: (2024)

Task-conditioned probing of instruction-tuned multimodal LLMs: Region-specific brain alignment patterns under naturalistic stimuli
by: Oota, Subba Reddy, et al.
Published: (2025)

What do vision-language models see in the context? Investigating multimodal in-context learning
by: Santos, Gabriel O. dos, et al.
Published: (2025)

Enhancing multimodal cooperation via sample-level modality valuation
by: Wei, Yake, et al.
Published: (2023)

Human alignment of neural network representations
by: Muttenthaler, Lukas, et al.
Published: (2022)

Review of multimodal machine learning approaches in healthcare
by: Krones, Felix, et al.
Published: (2024)

Vision CNNs trained to estimate spatial latents learned similar ventral-stream-aligned representations
by: Xie, Yudi, et al.
Published: (2024)

Understanding normalization in contrastive representation learning and out-of-distribution detection
by: Le-Gia, Tai, et al.
Published: (2023)

Explaining latent representations of generative models with large multimodal models
by: Zhu, Mengdan, et al.
Published: (2024)

MULTIAQUA: A multimodal maritime dataset and robust training strategies for multimodal semantic segmentation
by: Muhovič, Jon, et al.
Published: (2025)

Optimal transport unlocks end-to-end learning for single-molecule localization
by: Seailles, Romain, et al.
Published: (2025)

Learned feature representations are biased by complexity, learning order, position, and more
by: Lampinen, Andrew Kyle, et al.
Published: (2024)

Self-supervised video pretraining yields robust and more human-aligned visual representations
by: Parthasarathy, Nikhil, et al.
Published: (2022)

Multi-modal Co-learning for Earth Observation: Enhancing single-modality models via modality collaboration
by: Mena, Francisco, et al.
Published: (2025)

Reducing catastrophic forgetting of incremental learning in the absence of rehearsal memory with task-specific token
by: Choi, Young Jo, et al.
Published: (2024)

Cross-modal Affinity-aligned Multimodal Learning Analytics for Predicting Student Collaboration Satisfaction in Game-Based Learning
by: Tsai, Wen-Hsin, et al.
Published: (2026)

LayerSync: Self-aligning Intermediate Layers
by: Haghighi, Yasaman, et al.
Published: (2025)

Dimensions underlying the representational alignment of deep neural networks with humans
by: Mahner, Florian P., et al.
Published: (2024)

Learnable Cross-modal Knowledge Distillation for Multi-modal Learning with Missing Modality
by: Wang, Hu, et al.
Published: (2023)

The problems with using STNs to align CNN feature maps
by: Finnveden, Lukas, et al.
Published: (2020)

CLIP Behaves like a Bag-of-Words Model Cross-modally but not Uni-modally
by: Koishigarina, Darina, et al.
Published: (2025)