Cover Image

SafeRoPE: Risk-specific Head-wise Embedding Rotation for Safe Generation in Rectified Flow Transformers

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yang, Xiang, Li, Feifei, Zhang, Mi, Hong, Geng, You, Xiaoyu, Yang, Min
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Detect-and-Guide: Self-regulation of Diffusion Models for Safe Text-to-Image Generation via Guideline Token Optimization
by: Li, Feifei, et al.
Published: (2025)

Broken Memories: Detecting and Mitigating Memorization in Diffusion Models with Degraded Generations
by: Huang, Yuanmin, et al.
Published: (2026)

Spiral RoPE: Rotate Your Rotary Positional Embeddings in the 2D Plane
by: Liu, Haoyu, et al.
Published: (2026)

ReRoPE: Repurposing RoPE for Relative Camera Control
by: Li, Chunyang, et al.
Published: (2026)

SmartSight: Mitigating Hallucination in Video-LLMs Without Compromising Video Understanding via Temporal Attention Collapse
by: Sun, Yiming, et al.
Published: (2025)

Diffusion MRI Transformer with a Diffusion Space Rotary Positional Embedding (D-RoPE)
by: Kung, Gustavo Chau Loo, et al.
Published: (2026)

VideoRoPE: What Makes for Good Video Rotary Position Embedding?
by: Wei, Xilin, et al.
Published: (2025)

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation
by: Jing, Zonglei, et al.
Published: (2025)

Rectified Diffusion: Straightness Is Not Your Need in Rectified Flow
by: Wang, Fu-Yun, et al.
Published: (2024)

SafeAlign-VLA: A Negative-Enhanced Safe Alignment Framework for Risk-Aware Autonomous Driving
by: Tian, Kefei, et al.
Published: (2026)

SafeCFG: Controlling Harmful Features with Dynamic Safe Guidance for Safe Generation
by: Pan, Jiadong, et al.
Published: (2024)

FishRoPE: Projective Rotary Position Embeddings for Omnidirectional Visual Perception
by: Ahuja, Rahul, et al.
Published: (2026)

DeContext as Defense: Safe Image Editing in Diffusion Transformers
by: Shen, Linghui, et al.
Published: (2025)

Probabilistic Precipitation Nowcasting with Rectified Flow Transformers
by: Schusterbauer, Johannes, et al.
Published: (2026)

Safe Text-to-Image Generation: Simply Sanitize the Prompt Embedding
by: Qiu, Huming, et al.
Published: (2024)

FlowScene: Style-Consistent Indoor Scene Generation with Multimodal Graph Rectified Flow
by: Yang, Zhifei, et al.
Published: (2026)

RoPECraft: Training-Free Motion Transfer with Trajectory-Guided RoPE Optimization on Diffusion Transformers
by: Gokmen, Ahmet Berke, et al.
Published: (2025)

RoPeSLR: 3D RoPE-driven Sparse-LowRank Attention for Efficient Diffusion Transformers
by: Liu, Yuxi, et al.
Published: (2026)

Text-to-Image Rectified Flow as Plug-and-Play Priors
by: Yang, Xiaofeng, et al.
Published: (2024)

RF-HiT: Rectified Flow Hierarchical Transformer for General Medical Image Segmentation
by: Djouama, Ahmed Marouane, et al.
Published: (2026)

NAMI: Efficient Image Generation via Bridged Progressive Rectified Flow Transformers
by: Ma, Yuhang, et al.
Published: (2025)

Safe-Sora: Safe Text-to-Video Generation via Graphical Watermarking
by: Su, Zihan, et al.
Published: (2025)

Livatar-1: Real-Time Talking Heads Generation with Tailored Flow Matching
by: Liu, Haiyang, et al.
Published: (2025)

Generalization and Memorization in Rectified Flow
by: Rao, Mingxing, et al.
Published: (2026)

ComRoPE: Scalable and Robust Rotary Position Embedding Parameterized by Trainable Commuting Angle Matrices
by: Yu, Hao, et al.
Published: (2025)

Straighten Viscous Rectified Flow via Noise Optimization
by: Dai, Jimin, et al.
Published: (2025)

Scaling Rectified Flow Transformers for High-Resolution Image Synthesis
by: Esser, Patrick, et al.
Published: (2024)

EraseAnything: Enabling Concept Erasure in Rectified Flow Transformers
by: Gao, Daiheng, et al.
Published: (2024)

FluxSpace: Disentangled Semantic Editing in Rectified Flow Transformers
by: Dalva, Yusuf, et al.
Published: (2024)

SafeDreamer: Safe Reinforcement Learning with World Models
by: Huang, Weidong, et al.
Published: (2023)

Steering Rectified Flow Models in the Vector Field for Controlled Image Generation
by: Patel, Maitreya, et al.
Published: (2024)

MemRoPE: Training-Free Infinite Video Generation via Evolving Memory Tokens
by: Kim, Youngrae, et al.
Published: (2026)

Universal Prompt Optimizer for Safe Text-to-Image Generation
by: Wu, Zongyu, et al.
Published: (2024)

LoRAShop: Training-Free Multi-Concept Image Generation and Editing with Rectified Flow Transformers
by: Dalva, Yusuf, et al.
Published: (2025)

SLayR: Scene Layout Generation with Rectified Flow
by: Braunstein, Cameron, et al.
Published: (2024)

Safe-SD: Safe and Traceable Stable Diffusion with Text Prompt Trigger for Invisible Generative Watermarking
by: Ma, Zhiyuan, et al.
Published: (2024)

Infinity-RoPE: Action-Controllable Infinite Video Generation Emerges From Autoregressive Self-Rollout
by: Yesiltepe, Hidir, et al.
Published: (2025)

SafeGen: Mitigating Sexually Explicit Content Generation in Text-to-Image Models
by: Li, Xinfeng, et al.
Published: (2024)

SemFlow: Binding Semantic Segmentation and Image Synthesis via Rectified Flow
by: Wang, Chaoyang, et al.
Published: (2024)

Offline Preference Optimization for Rectified Flow with Noise-Tracked Pairs
by: Lu, Yunhong, et al.
Published: (2026)