Paper Detail

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

Sana Tonekaboni, Viktoria Schuster, Caroline Uhler

Browse

Workflow Queues

arxiv Score 9.8

Published 2026-07-18 · First seen 2026-07-21

General AI

Open paper source

Abstract

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 multimodal training difficult. Second, existing multimodal representations frequently entangle information shared across modalities with modality-specific information, hindering interpretability and control. We introduce MultiLoReFT, an efficient and scalable low-rank representation fine-tuning framework for multimodal learning with pretrained unimodal models. MultiLoReFT extends low-rank adaptation to the multimodal setting and learns interpretable projection subspaces that decouple shared and modality-specific information. Across simulated and real-world benchmarks, it produces representations that support multimodal prediction while explicitly revealing how shared and modality-specific information is distributed across modalities.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
soon
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

Similar Papers

Scalable Variational Bayesian Fine-Tuning of LLMs via Orthogonalized Low-Rank Adapters 2026-04-03 · Score 8.3 General AI SLORR: Simple and Efficient In-Training Low-Rank Regularization 2026-07-09 · Score 4.3 General AI Low-Rank Adaptation for Critic Learning in Off-Policy Reinforcement Learning 2026-04-21 · Score 9.3 General AI Cross-Modal Bayesian Low-Rank Adaptation for Uncertainty-Aware Multimodal Learning 2026-04-17 · Score 5.3 General AI Learning to Reason by Analogy via Retrieval-Augmented Reinforcement Fine-Tuning 2026-06-11 · Score 13.8 General AI

BibTeX

@article{tonekaboni2026multiloreft,
  title = {MultiLoReFT: Decoupling Shared and Modality-Specific Subspaces in Multimodal Learning via Low-Rank Representation Fine-Tuning},
  author = {Sana Tonekaboni and Viktoria Schuster and Caroline Uhler},
  year = {2026},
  abstract = {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 multimodal training difficult. Second, existing multimodal representations frequently entangle information shared across modalities with modality-specific information, hindering interpretability and contro},
  url = {https://arxiv.org/abs/2607.16789},
  keywords = {cs.LG},
  eprint = {2607.16789},
  archiveprefix = {arXiv},
}

Metadata

{}