Cover Image

Where and How to Perturb: On the Design of Perturbation Guidance in Diffusion and Flow Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ahn, Donghoon, Kang, Jiwon, Lee, Sanghyun, Kim, Minjae, Min, Jaewon, Jang, Wooseok, Lee, Sangwu, Paul, Sayak, Hong, Susung, Kim, Seungryong
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

A Noise is Worth Diffusion Guidance
by: Ahn, Donghoon, et al.
Published: (2024)

Self-Rectifying Diffusion Sampling with Perturbed-Attention Guidance
by: Ahn, Donghoon, et al.
Published: (2024)

TAG: Tangential Amplifying Guidance for Hallucination-Resistant Sampling
by: Cho, Hyunmin, et al.
Published: (2025)

Retrieval-Augmented Score Distillation for Text-to-3D Generation
by: Seo, Junyoung, et al.
Published: (2024)

APPLE: Attribute-Preserving Pseudo-Labeling for Diffusion-Based Face Swapping
by: Kang, Jiwon, et al.
Published: (2026)

DA-Flow: Degradation-Aware Optical Flow Estimation with Diffusion Models
by: Min, Jaewon, et al.
Published: (2026)

WorldKV: Efficient World Memory with World Retrieval and Compression
by: Yi, Jung, et al.
Published: (2026)

Smoothed Energy Guidance: Guiding Diffusion Models with Reduced Energy Curvature of Attention
by: Hong, Susung
Published: (2024)

Spatiotemporal Skip Guidance for Enhanced Video Diffusion Sampling
by: Hyung, Junha, et al.
Published: (2024)

Domain Generalization Using Large Pretrained Models with Mixture-of-Adapters
by: Lee, Gyuseong, et al.
Published: (2023)

Identity-preserving Distillation Sampling by Fixed-Point Iterator
by: Kim, SeonHwa, et al.
Published: (2025)

ControlFace: Harnessing Facial Parametric Control for Face Rigging
by: Jang, Wooseok, et al.
Published: (2024)

Lookahead Unmasking Elicits Accurate Decoding in Diffusion Language Models
by: Lee, Sanghyun, et al.
Published: (2025)

V-Warper: Appearance-Consistent Video Diffusion Personalization via Value Warping
by: Lee, Hyunkoo, et al.
Published: (2025)

Effective Test-Time Scaling of Discrete Diffusion through Iterative Refinement
by: Lee, Sanghyun, et al.
Published: (2025)

DirecT2V: Large Language Models are Frame-Level Directors for Zero-Shot Text-to-Video Generation
by: Hong, Susung, et al.
Published: (2023)

Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generation
by: Seo, Junyoung, et al.
Published: (2023)

Geometry-Aware Score Distillation via 3D Consistent Noising and Gradient Consistency Modeling
by: Kwak, Min-Seop, et al.
Published: (2024)

Unified Diffusion Transformer for High-fidelity Text-Aware Image Restoration
by: Kim, Jin Hyeon, et al.
Published: (2025)

Set-Based Position Ambiguity Reduction Method for Zonotope Shadow Matching in Urban Areas Using Estimated Multipath Errors
by: Kim, Sanghyun, et al.
Published: (2025)

Zonotope Shadow and Reflection Matching: A Novel GNSS Reflection-Based Framework for Enhanced Positioning Accuracy in Urban Areas
by: Kim, Sanghyun, et al.
Published: (2026)

Enhancing Urban GNSS Positioning Reliability via Conservative Satellite Selection Using Unanimous Voting Across Multiple Machine Learning Classifiers
by: Kim, Sanghyun, et al.
Published: (2025)

Perturb-and-Revise: Flexible 3D Editing with Generative Trajectories
by: Hong, Susung, et al.
Published: (2024)

Text-Aware Image Restoration with Diffusion Models
by: Min, Jaewon, et al.
Published: (2025)

Token Perturbation Guidance for Diffusion Models
by: Rajabi, Javad, et al.
Published: (2025)

Deep Forcing: Training-Free Long Video Generation with Deep Sink and Participative Compression
by: Yi, Jung, et al.
Published: (2025)

MAGIC: Few-Shot Mask-Guided Anomaly Inpainting with Prompt Perturbation, Spatially Adaptive Guidance, and Context Awareness
by: Choi, JaeHyuck, et al.
Published: (2025)

7‐2: Distinguished Paper: Effective 10‐bit OLED Driver IC with 11‐bit DAC, Double Capacitor‐Coupled Adder, and Offset Calibration for Enhanced Panel Driving
by: Changwhan Kim, et al.
Published: (2025)

Follow-the-Perturbed-Leader for Decoupled Bandits: Best-of-Both-Worlds and Practicality
by: Kim, Chaiwon, et al.
Published: (2025)

Tidiness Score-Guided Monte Carlo Tree Search for Visual Tabletop Rearrangement
by: Kee, Hogun, et al.
Published: (2025)

Insight into C4 Selectivity in the Light‐Driven C−H Fluoroalkylation of Pyridines and Quinolines
by: Leejae Kim, et al.
Published: (2024)

Insight into C4 Selectivity in the Light‐Driven C−H Fluoroalkylation of Pyridines and Quinolines
by: Leejae Kim, et al.
Published: (2024)

Repurposing Geometric Foundation Models for Multi-view Diffusion
by: Jang, Wooseok, et al.
Published: (2026)

Quantum Support Vector Machine-Based Classification of GPS Signal Reception Conditions
by: Jeong, Suhui, et al.
Published: (2024)

Understanding and Accelerating the Training of Masked Diffusion Language Models
by: Hong, Chunsan, et al.
Published: (2026)

Point-Cloud Based Inverse Design of Free-Form Metamaterials Using Deep Generative Networks
by: Kim, Kijung, et al.
Published: (2024)

Revisiting Follow-the-Perturbed-Leader with Unbounded Perturbations in Bandit Problems
by: Lee, Jongyeong, et al.
Published: (2025)

SPG: Improving Motion Diffusion by Smooth Perturbation Guidance
by: Jeon, Boseong
Published: (2025)

Emergent Outlier View Rejection in Visual Geometry Grounded Transformers
by: Han, Jisang, et al.
Published: (2025)

Manifold-Constrained MPPI: Real-Time Sampling-Based Control Under Hard Constraints
by: Lee, Seulchan, et al.
Published: (2026)