AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Transformed Low-rank Adaptation via Tensor Decomposition and Its Applications to Text-to-image Models

Zerui Tao, Yuhta Takida, Naoki Murata, Qibin Zhao, Yuki Mitsufuji

ICCV 2025 · Architectures and efficiency › Pruning and efficient tuning · approach: LoRA variants and theory · 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 TRM transform on top of LoRA rank 4 (ablation)LoRA · Segmentation-to-image (ADE20K)mIoU: 27.72 -> 29.23Improved
add TRM transform on top of LoRA rank 4 (ablation)LoRA · Segmentation-to-image (ADE20K)aACC: 64.99 -> 69.21Improved
add TRM transform on top of LoRA rank 4 (ablation)LoRA · Canny-to-image (ADE20K)IoU: 0.180 -> 0.203Improved
add TRM transform on top of LoRA rank 4 (ablation)LoRA · Landmark-to-image (CelebA-HQ)error: 5.32 -> 5.32No clear effect
add diagonal magnitude (DoRA) to LoRALoRA · Landmark-to-image (CelebA-HQ)error: 5.32 -> 6.43Hurt
use TR residual rank 8 with TRM instead of LoRA residual, fewer parametersTLoRA · Segmentation-to-image (ADE20K)mIoU: 29.23 -> 27.42Hurt
replace LoRETTA (non-zero init TR) with TLoRA TR residual with zero initLoRETTA · Landmark-to-image (CelebA-HQ)error: 118.14 -> 5.84Improved
add identity regularization on the transformTLoRA · controllable generationqualityImproved
use TRM transform instead of OFT block-diagonal transform with LoRA (ablation)LoRA · simulation SDXL weightsapproximation errorImproved
use TLoRA(2,6) instead of OFT r=32 to cut parametersOFT · Canny-to-image (ADE20K)IoU: 0.165 -> 0.184Improved
use TLoRA with TRM + TR rank 2 for SDXL subject-driven generation instead of LoRA r=1LoRA · DreamBooth subject-drivenparameters (M): 1.45 -> 0.40Improved
add TRM transform to LoRA (ablation)LoRA · training speedIter./Sec.: 0.58 -> 0.37Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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