Image de couverture de livre

CFG-Zero*: Improved Classifier-Free Guidance for Flow Matching Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Fan, Weichen, Zheng, Amber Yijia, Yeh, Raymond A., Liu, Ziwei
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

Multi-concept Model Immunization through Differentiable Model Merging
par: Zheng, Amber Yijia, et autres
Publié: (2024)

IMMA: Immunizing text-to-image Models against Malicious Adaptation
par: Zheng, Amber Yijia, et autres
Publié: (2023)

CFG-Ctrl: Control-Based Classifier-Free Diffusion Guidance
par: Wang, Hanyang, et autres
Publié: (2026)

CFG++: Manifold-constrained Classifier Free Guidance for Diffusion Models
par: Chung, Hyungjin, et autres
Publié: (2024)

EP-CFG: Energy-Preserving Classifier-Free Guidance
par: Zhang, Kai, et autres
Publié: (2024)

Designing to Forget: Deep Semi-parametric Models for Unlearning
par: Zheng, Amber Yijia, et autres
Publié: (2026)

Learning to Obstruct Few-Shot Image Classification over Restricted Classes
par: Zheng, Amber Yijia, et autres
Publié: (2024)

Improving Classifier-Free Guidance of Flow Matching via Manifold Projection
par: Cai, Jian-Feng, et autres
Publié: (2026)

Rectified-CFG++ for Flow Based Models
par: Saini, Shreshth, et autres
Publié: (2025)

SoftCFG: Uncertainty-guided Stable Guidance for Visual Autoregressive Model
par: Xu, Dongli, et autres
Publié: (2025)

SafeCFG: Controlling Harmful Features with Dynamic Safe Guidance for Safe Generation
par: Pan, Jiadong, et autres
Publié: (2024)

Decoupled DMD: CFG Augmentation as the Spear, Distribution Matching as the Shield
par: Liu, Dongyang, et autres
Publié: (2025)

DarkDiff: Advancing Low-Light Raw Enhancement by Retasking Diffusion Models for Camera ISP
par: Zheng, Amber Yijia, et autres
Publié: (2025)

WebAccessVL: Violation-Aware VLM for Web Accessibility
par: Zheng, Amber Yijia, et autres
Publié: (2025)

Contrastive CFG: Improving CFG in Diffusion Models by Contrasting Positive and Negative Concepts
par: Chang, Jinho, et autres
Publié: (2024)

Rethinking Preference Alignment for Diffusion Models with Classifier-Free Guidance
par: Jiang, Zhou, et autres
Publié: (2026)

Towards Understanding the Mechanisms of Classifier-Free Guidance
par: Li, Xiang, et autres
Publié: (2025)

Tuning-Free Amodal Segmentation via the Occlusion-Free Bias of Inpainting Models
par: Lee, Jae Joong, et autres
Publié: (2025)

Factored Classifier-Free Guidance
par: Xia, Tian, et autres
Publié: (2025)

Deep Nets with Subsampling Layers Unwittingly Discard Useful Activations at Test-Time
par: Yang, Chiao-An, et autres
Publié: (2024)

DICE: Distilling Classifier-Free Guidance into Text Embeddings
par: Zhou, Zhenyu, et autres
Publié: (2025)

Gradient-Free Classifier Guidance for Diffusion Model Sampling
par: Shenoy, Rahul, et autres
Publié: (2024)

Rethinking Oversaturation in Classifier-Free Guidance via Low Frequency
par: Song, Kaiyu, et autres
Publié: (2025)

Rethinking the Spatial Inconsistency in Classifier-Free Diffusion Guidance
par: Shen, Dazhong, et autres
Publié: (2024)

The Prism Hypothesis: Harmonizing Semantic and Pixel Representations via Unified Autoencoding
par: Fan, Weichen, et autres
Publié: (2025)

No Training, No Problem: Rethinking Classifier-Free Guidance for Diffusion Models
par: Sadat, Seyedmorteza, et autres
Publié: (2024)

Value Gradient Guidance for Flow Matching Alignment
par: Liu, Zhen, et autres
Publié: (2025)

Analysis of Classifier-Free Guidance Weight Schedulers
par: Wang, Xi, et autres
Publié: (2024)

TeEFusion: Blending Text Embeddings to Distill Classifier-Free Guidance
par: Fu, Minghao, et autres
Publié: (2025)

NorMatch: Matching Normalizing Flows with Discriminative Classifiers for Semi-Supervised Learning
par: Deng, Zhongying, et autres
Publié: (2022)

UniFlowRestore: A General Video Restoration Framework via Flow Matching and Prompt Guidance
par: Sun, Shuning, et autres
Publié: (2025)

Blockwise Flow Matching: Improving Flow Matching Models For Efficient High-Quality Generation
par: Park, Dogyun, et autres
Publié: (2025)

Efficient Distillation of Classifier-Free Guidance using Adapters
par: Jensen, Cristian Perez, et autres
Publié: (2025)

Flow Matching with Uncertainty Quantification and Guidance
par: Han, Juyeop, et autres
Publié: (2026)

AdaptInfer: Adaptive Token Pruning for Vision-Language Model Inference with Dynamical Text Guidance
par: Zhang, Weichen, et autres
Publié: (2025)

RepVideo: Rethinking Cross-Layer Representation for Video Generation
par: Si, Chenyang, et autres
Publié: (2025)

FlowMotion: Training-Free Flow Guidance for Video Motion Transfer
par: Wang, Zhen, et autres
Publié: (2026)

How Much To Guide: Revisiting Adaptive Guidance in Classifier-Free Guidance Text-to-Vision Diffusion Models
par: Zhang, Huixuan, et autres
Publié: (2025)

RectifID: Personalizing Rectified Flow with Anchored Classifier Guidance
par: Sun, Zhicheng, et autres
Publié: (2024)

Dynamic Classifier-Free Diffusion Guidance via Online Feedback
par: Papalampidi, Pinelopi, et autres
Publié: (2025)