AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

MoRA: Missing Modality Low-Rank Adaptation for Visual Recognition

Shu Zhao, Nilesh Ahuja, Tan Yu, Tianyi Shen, Vijaykrishnan Narayanan

ICLR 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Test-time adaptation of VLMs · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add Gram matrices for cross-modal sharing (ablation)MoRA · Food101 (70% missing, both modalities missing)accuracy: 80.31 -> 83.77Improved
add modality-specific parameters (ablation)MoRA · Food101 (70% missing, both modalities missing)accuracy: 81.32 -> 83.77Improved
share parameters across modalities instead of independent ones (ablation)MoRA · Food101 (70% missing, both modalities missing)accuracyImproved
use Gram matrices instead of linear projection (Align) (ablation)MoRA · Food101 (70% missing, both modalities missing)accuracy: 81.14 -> 83.77Improved
use Gram matrices instead of concatenation fusion (ablation)MoRA · Food101 (70% missing, both modalities missing)accuracy: 81.01 -> 83.77Improved
use fixed Gram matrix instead of learnable one (ablation)MoRA · Food101 (70% missing, both modalities missing)accuracy: 83.37 -> 83.77Improved
add frozen W0 into the shared branch (ablation)MoRA · Food101 (70% missing, both modalities missing)accuracy: 83.77 -> 83.59No clear effect
attach MoRA to rear layers instead of front layers (ablation)MoRA · Food101 (70% missing, both modalities missing)accuracy: 81.08 -> 83.77Improved
attach MoRA to rear layers instead of middle layers (ablation)MoRA · Food101 (70% missing, both modalities missing)accuracy: 82.48 -> 83.77Improved
use MoRA instead of LoRALoRA · Food101 (70% missing, both modalities missing)accuracy: 82.14 -> 83.77Improved
use MoRA instead of full fine-tuningFFT · Food101 (70% missing, both modalities missing)accuracy: 14.05 -> 83.77Improved
add MoRA to CLIP4CIRCLIP4CIR · MS-COCO image-to-image retrievalRecall@1: 43.34 -> 60.50Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy