Author

Sana Tonekaboni

h-index 1 View on Semantic Scholar

We have 2 of 6 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

FiGuRO: Intrinsic Dimension Estimation for Multi-Modal Data

Fidelity-Guided Rank Optimization (FiGuRO), a framework for approximating the ID of uni- and multi-modal data under constraints of model capacity and hyperparameters, is introduced and can be applied to modern uni-modal pretrained models, enabling efficient, post-hoc disentanglement of multi-modal representations.

Viktoria Schuster, Sana Tonekaboni, Caroline Uhler · 0 citations

Jul 2026

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

This work introduces MultiLoReFT, an efficient and scalable low-rank representation fine-tuning framework for multimodal learning with pretrained unimodal models that produces representations that support multimodal prediction while explicitly revealing how shared and modality-specific information is distributed across...

Sana Tonekaboni, Viktoria Schuster, Caroline Uhler · arXiv.org · 1 citation