AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

LoRAverse: A Submodular Framework to Retrieve Diverse Adapters for Diffusion Models

Mert Sonmezer, Matthew Zheng, Pinar Yanardag

ICCV 2025 · Architectures and efficiency › Pruning and efficient tuning · approach: LoRA variants and theory · 2 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
use LoRAverse submodular retrieval instead of StylusStable Diffusion with LoRA retrieval · MS-COCO + PartiPrompts (CFG=7)TCE: 20.30 -> 22.63Improved
use LoRAverse submodular retrieval instead of StylusStable Diffusion with LoRA retrieval · MS-COCO + PartiPrompts (CFG=7)TIE: 38.53 -> 40.06Improved
use LoRAverse submodular retrieval instead of StylusStable Diffusion with LoRA retrieval · MS-COCO + PartiPrompts (CFG=7)I2I: 0.825 -> 0.784Improved
use LoRAverse submodular retrieval instead of StylusStable Diffusion with LoRA retrieval · MS-COCO + PartiPrompts (CFG=7)CLIP: 25.41 -> 25.07Hurt
use LoRAverse instead of StylusStable Diffusion with LoRA retrieval · User studyUS-D: 2.82 -> 3.92Improved
use LoRAverse instead of StylusStable Diffusion with LoRA retrieval · User studyUS-F: 3.71 -> 3.78No clear effect
use LoRAverse instead of StylusStable Diffusion with LoRA retrieval · User studyUS-P: 29.90% -> 47.55%Improved
use submodular retrieval instead of cosine similarity retrieval (ablation)LoRAverse · Retrieval ablation (520 images)TCE: 23.47 -> 23.97Improved
use submodular retrieval instead of cosine similarity retrieval (ablation)LoRAverse · Retrieval ablation (520 images)I2I: 0.781 -> 0.762Improved
use submodular retrieval instead of cosine similarity retrieval (ablation)LoRAverse · Retrieval ablation (520 images)CLIP: 24.67 -> 24.50Hurt
use submodular retrieval instead of RTop-100 random sampling (ablation)LoRAverse · Additional baselines (K=8)TIE: 42.40 -> 43.04Improved
use submodular retrieval instead of RTop-100 random sampling (ablation)LoRAverse · Additional baselines (K=8)CLIP: 24.99 -> 24.94No clear effect

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