Image de couverture de livre

ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Guo, Xiefan, Cui, Miaomiao, Bo, Liefeng, Huang, Di
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

I4VGen: Image as Free Stepping Stone for Text-to-Video Generation
par: Guo, Xiefan, et autres
Publié: (2024)

InitNO: Boosting Text-to-Image Diffusion Models via Initial Noise Optimization
par: Guo, Xiefan, et autres
Publié: (2024)

Spatial Gram Alignment for Ultra-High-Resolution Image Synthesis
par: Zhang, Jinjin, et autres
Publié: (2026)

CTCal: Rethinking Text-to-Image Diffusion Models via Cross-Timestep Self-Calibration
par: Guo, Xiefan, et autres
Publié: (2026)

GaussianIP: Identity-Preserving Realistic 3D Human Generation via Human-Centric Diffusion Prior
par: Tang, Zichen, et autres
Publié: (2025)

Towards Fine-grained Interactive Segmentation in Images and Videos
par: Yao, Yuan, et autres
Publié: (2025)

MIMO: Controllable Character Video Synthesis with Spatial Decomposed Modeling
par: Men, Yifang, et autres
Publié: (2024)

Perception-as-Control: Fine-grained Controllable Image Animation with 3D-aware Motion Representation
par: Chen, Yingjie, et autres
Publié: (2025)

Image Inpainting via Conditional Texture and Structure Dual Generation
par: Guo, Xiefan, et autres
Publié: (2021)

Diffusion-4K: Ultra-High-Resolution Image Synthesis with Latent Diffusion Models
par: Zhang, Jinjin, et autres
Publié: (2025)

EruDiff: Refactoring Knowledge in Diffusion Models for Advanced Text-to-Image Synthesis
par: Guo, Xiefan, et autres
Publié: (2026)

MoSAM: Motion-Guided Segment Anything Model with Spatial-Temporal Memory Selection
par: Yang, Qiushi, et autres
Publié: (2025)

Disentangling Foreground and Background Motion for Enhanced Realism in Human Video Generation
par: Liu, Jinlin, et autres
Publié: (2024)

RB-FT: Rationale-Bootstrapped Fine-Tuning for Video Classification
par: Xu, Meilong, et autres
Publié: (2025)

Ultra-High-Resolution Image Synthesis: Data, Method and Evaluation
par: Zhang, Jinjin, et autres
Publié: (2025)

DiffuEraser: A Diffusion Model for Video Inpainting
par: Li, Xiaowen, et autres
Publié: (2025)

What Makes Synthetic Data Effective in Image Segmentation
par: Zhang, Jinjin, et autres
Publié: (2026)

Cross-Frame Representation Alignment for Fine-Tuning Video Diffusion Models
par: Hwang, Sungwon, et autres
Publié: (2025)

StarFT: Robust Fine-tuning of Zero-shot Models via Spuriosity Alignment
par: Kim, Younghyun, et autres
Publié: (2025)

SCoFT: Self-Contrastive Fine-Tuning for Equitable Image Generation
par: Liu, Zhixuan, et autres
Publié: (2024)

S2FT: Parameter-Efficient Fine-Tuning in Sparse Spectrum Domain
par: Zhang, Baoquan, et autres
Publié: (2026)

CReFT-CAD: Boosting Orthographic Projection Reasoning for CAD via Reinforcement Fine-Tuning
par: Niu, Ke, et autres
Publié: (2025)

AutoFT: Learning an Objective for Robust Fine-Tuning
par: Choi, Caroline, et autres
Publié: (2024)

SHIFT: Motion Alignment in Video Diffusion Models with Adversarial Hybrid Fine-Tuning
par: Ye, Xi, et autres
Publié: (2026)

EMO: Emote Portrait Alive -- Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions
par: Tian, Linrui, et autres
Publié: (2024)

FT-Shield: A Watermark Against Unauthorized Fine-tuning in Text-to-Image Diffusion Models
par: Cui, Yingqian, et autres
Publié: (2023)

One Step Diffusion via Shortcut Models
par: Frans, Kevin, et autres
Publié: (2024)

AdaptiveDrag: Semantic-Driven Dragging on Diffusion-Based Image Editing
par: Chen, DuoSheng, et autres
Publié: (2024)

Enhancing Diffusion-based Unrestricted Adversarial Attacks via Adversary Preferences Alignment
par: Jiang, Kaixun, et autres
Publié: (2025)

Learning to Think in Physics: Breaking Shortcut Learning in Scientific Diffusion via Representation Alignment
par: Jia, Haozhe, et autres
Publié: (2026)

ChatAnyone: Stylized Real-time Portrait Video Generation with Hierarchical Motion Diffusion Model
par: Qi, Jinwei, et autres
Publié: (2025)

Lipsum-FT: Robust Fine-Tuning of Zero-Shot Models Using Random Text Guidance
par: Nam, Giung, et autres
Publié: (2024)

SleeperMark: Towards Robust Watermark against Fine-Tuning Text-to-image Diffusion Models
par: Wang, Zilan, et autres
Publié: (2024)

LiFT: Leveraging Human Feedback for Text-to-Video Model Alignment
par: Wang, Yibin, et autres
Publié: (2024)

VARD: Efficient and Dense Fine-Tuning for Diffusion Models with Value-based RL
par: Dai, Fengyuan, et autres
Publié: (2025)

Self-NPO: Data-Free Diffusion Model Enhancement via Truncated Diffusion Fine-Tuning
par: Wang, Fu-Yun, et autres
Publié: (2025)

AnyText2: Visual Text Generation and Editing With Customizable Attributes
par: Tuo, Yuxiang, et autres
Publié: (2024)

UniPortrait: A Unified Framework for Identity-Preserving Single- and Multi-Human Image Personalization
par: He, Junjie, et autres
Publié: (2024)

LoFT: Parameter-Efficient Fine-Tuning for Long-tailed Semi-Supervised Learning in Open-World Scenarios
par: Huang, Zhiyuan, et autres
Publié: (2025)

MedDiff-FT: Data-Efficient Diffusion Model Fine-tuning with Structural Guidance for Controllable Medical Image Synthesis
par: Xie, Jianhao, et autres
Publié: (2025)