5 papers
FiGuRO: Intrinsic Dimension Estimation for Multi-Modal Data
Viktoria Schuster, Sana Tonekaboni, Caroline Uhler
Determining the complexity, or Intrinsic Dimension (ID), of data is fundamental to efficient and interpretable representation learning. This is particularly challenging in multi-mo…
MultiLoReFT: Decoupling Shared and Modality-Specific Subspaces in Multimodal Learning via Low-Rank Representation Fine-Tuning
Sana Tonekaboni, Viktoria Schuster, Caroline Uhler
Real-world perception and decision making are inherently multimodal, integrating complementary signals across modalities. However, training multimodal models faces two main obstacl…
BindEnergyCraft: Casting Protein Structure Predictors as Energy-Based Models for Binder Design
Divya Nori, Anisha Parsan, Caroline Uhler +1
Protein binder design has been transformed by hallucination-based methods that optimize structure prediction confidence metrics, such as the interface predicted TM-score (ipTM), vi…
An Information Criterion for Controlled Disentanglement of Multimodal Data
Chenyu Wang, Sharut Gupta, Xinyi Zhang +4
Multimodal representation learning seeks to relate and decompose information inherent in multiple modalities. By disentangling modality-specific information from information that i…
Identifiability Guarantees for Causal Disentanglement from Purely Observational Data
Ryan Welch, Jiaqi Zhang, Caroline Uhler
Causal disentanglement aims to learn about latent causal factors behind data, holding the promise to augment existing representation learning methods in terms of interpretability a…