AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

Fine-Tuning Visual Autogressive Models for Subject-Driven Generation

Jiwoo Chung, Sangeek Hyun, Hyunjun Kim, Eunseo Koh, MinKyu Lee, Jae-Pil Heo

ICCV 2025 · Image generation › Text-to-image diffusion · approach: Compositional text-to-image guidance

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
tune only CA and FFN layers instead of all layers (ablation)ARBooth (Infinity-2B) · 5 living subjectsPRES / DIV: PRES 0.776 -> 0.709; DIV 0.254 -> 0.272Improved
add scale-wise weighted tuning (down-weight scales above 8 to 0.5) (ablation)ARBooth · 5 living subjectsI_dino: 0.774 -> 0.786 I_dino; PRES 0.792 -> 0.709; T_clip 0.271 -> 0.267Improved
add prior distillation (ablation)ARBooth · 5 living subjectsPRES / DIV: PRES 0.839 -> 0.709; DIV 0.209 -> 0.272; I_dino 0.823 -> 0.786Improved
replace prior distillation with prior preservation loss (class images) (ablation)ARBooth · 5 living subjectsI_dino / DIV: I_dino 0.786 -> 0.653; DIV 0.272 -> 0.378No clear effect
use LoRA on all layers without selective layer tuning or prior distillation (ablation)ARBooth · 5 living subjectssubject fidelity: LoRA(4) I_dino 0.653 vs 0.786Hurt
use ARBooth on Infinity-2B instead of diffusion-based personalization baselinessubject-driven generation · ViCo datasetI_dino: 0.682 (DM) -> 0.705Improved
use ARBooth instead of DreamBooth on recent diffusion models (SD3.5, FLUX)subject-driven generation · 5 living subjectsI_dino: 0.730 (SD3.5-md Full) -> 0.786; time 15s -> 0.5sImproved
use ARBooth instead of SD3.5-medium LoRAsubject-driven generation · 5 living subjectsT_clip: 0.275 -> 0.267Hurt

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