Viktoria Schuster — accepted AI-conference papers

2026

FiGuRO - Intrinsic Dimension Estimation for Multi-Modal Data

Viktoria Schuster, Sana Tonekaboni, Caroline Uhler

ICML 2026poster

Determining the complexity, or Intrinsic Dimension (ID), of data is fundamental to efficient and interpretable representation learning. This is particularly challenging in multi-modal settings when trying to learn disentangled representations for shared and private information. Existing techniques l…

Cited by 0 Source ↗Scholar ↗

2026

MultiLoReFT: Decoupling Shared and Modality-Specific Subspaces in Multimodal Learning via Low-Rank Representation Fine-Tuning

Sana Tonekaboni, Viktoria Schuster, Caroline Uhler

ICML 2026poster

Real-world perception and decision making are inherently multimodal, integrating complementary signals across modalities. However, training multimodal models faces two main obstacles. First, collecting large-scale, well-aligned paired multimodal datasets is often impractical, making end-to-end multi…

Cited by 0 Source ↗Scholar ↗