Copertina

SafeEditor: Unified MLLM for Efficient Post-hoc T2I Safety Editing

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhang, Ruiyang, Luo, Jiahao, Feng, Xiaoru, Pang, Qiufan, Yang, Yaodong, Dai, Juntao
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

InstructX: Towards Unified Visual Editing with MLLM Guidance
di: Mou, Chong, et al.
Pubblicazione: (2025)

Omni-Video 2: Scaling MLLM-Conditioned Diffusion for Unified Video Generation and Editing
di: Yang, Hao, et al.
Pubblicazione: (2026)

Single-weight Model Editing for Post-hoc Spurious Correlation Neutralization
di: Hakemi, Shahin, et al.
Pubblicazione: (2025)

CAD-MLLM: Unifying Multimodality-Conditioned CAD Generation With MLLM
di: Xu, Jingwei, et al.
Pubblicazione: (2024)

SafeSora: Towards Safety Alignment of Text2Video Generation via a Human Preference Dataset
di: Dai, Josef, et al.
Pubblicazione: (2024)

SmartPhotoCrafter: Unified Reasoning, Generation and Optimization for Automatic Photographic Image Editing
di: Zeng, Ying, et al.
Pubblicazione: (2026)

PUMA: Empowering Unified MLLM with Multi-granular Visual Generation
di: Fang, Rongyao, et al.
Pubblicazione: (2024)

VLA-Arena: An Open-Source Framework for Benchmarking Vision-Language-Action Models
di: Zhang, Borong, et al.
Pubblicazione: (2025)

Moodifier: MLLM-Enhanced Emotion-Driven Image Editing
di: Ye, Jiarong, et al.
Pubblicazione: (2025)

Post-hoc Part-prototype Networks
di: Tan, Andong, et al.
Pubblicazione: (2024)

POEM: Precise Object-level Editing via MLLM control
di: Schouten, Marco, et al.
Pubblicazione: (2025)

PostEdit: Posterior Sampling for Efficient Zero-Shot Image Editing
di: Tian, Feng, et al.
Pubblicazione: (2024)

RoboSafe: Safeguarding Embodied Agents via Executable Safety Logic
di: Wang, Le, et al.
Pubblicazione: (2025)

ShapeMamba-EM: Fine-Tuning Foundation Model with Local Shape Descriptors and Mamba Blocks for 3D EM Image Segmentation
di: Shi, Ruohua, et al.
Pubblicazione: (2024)

ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion Refinement
di: Huang, Runhui, et al.
Pubblicazione: (2025)

MIND-Edit: MLLM Insight-Driven Editing via Language-Vision Projection
di: Wang, Shuyu, et al.
Pubblicazione: (2025)

Efficient Motion-Aware Video MLLM
di: Zhao, Zijia, et al.
Pubblicazione: (2025)

Post-hoc Self-explanation of CNNs
di: Boubekki, Ahcène, et al.
Pubblicazione: (2026)

Towards Reason-Informed Video Editing in Unified Models with Self-Reflective Learning
di: Liu, Xinyu, et al.
Pubblicazione: (2025)

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

REALM: An MLLM-Agent Framework for Open World 3D Reasoning Segmentation and Editing on Gaussian Splatting
di: Shi, Changyue, et al.
Pubblicazione: (2025)

The Evolution of Video Anomaly Detection: A Unified Framework from DNN to MLLM
di: Gao, Shibo, et al.
Pubblicazione: (2025)

MLLM-Protector: Ensuring MLLM's Safety without Hurting Performance
di: Pi, Renjie, et al.
Pubblicazione: (2024)

UNIC: Unified In-Context Video Editing
di: Ye, Zixuan, et al.
Pubblicazione: (2025)

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

Saliency-R1: Incentivizing Unified Saliency Reasoning Capability in MLLM with Confidence-Guided Reinforcement Learning
di: Li, Long, et al.
Pubblicazione: (2025)

MLLM-4D: Towards Visual-based Spatial-Temporal Intelligence
di: Yin, Xingyilang, et al.
Pubblicazione: (2026)

Uniworld-V2: Reinforce Image Editing with Diffusion Negative-aware Finetuning and MLLM Implicit Feedback
di: Li, Zongjian, et al.
Pubblicazione: (2025)

Post-hoc Probabilistic Vision-Language Models
di: Baumann, Anton, et al.
Pubblicazione: (2024)

Lego-Edit: A General Image Editing Framework with Model-Level Bricks and MLLM Builder
di: Jia, Qifei, et al.
Pubblicazione: (2025)

When Privacy Meets Recovery: The Overlooked Half of Surrogate-Driven Privacy Preservation for MLLM Editing
di: Xu, Siyuan, et al.
Pubblicazione: (2025)

EMMA: Efficient Multimodal Understanding, Generation, and Editing with a Unified Architecture
di: He, Xin, et al.
Pubblicazione: (2025)

Drone Referring Localization: An Efficient Heterogeneous Spatial Feature Interaction Method For UAV Self-Localization
di: Dai, Ming, et al.
Pubblicazione: (2022)

DriveEditor: A Unified 3D Information-Guided Framework for Controllable Object Editing in Driving Scenes
di: Liang, Yiyuan, et al.
Pubblicazione: (2024)

UniEdit-I: Training-free Image Editing for Unified VLM via Iterative Understanding, Editing and Verifying
di: Bai, Chengyu, et al.
Pubblicazione: (2025)

VisionTrim: Unified Vision Token Compression for Training-Free MLLM Acceleration
di: Yu, Hanxun, et al.
Pubblicazione: (2026)

MSJoE: Jointly Evolving MLLM and Sampler for Efficient Long-Form Video Understanding
di: Tan, Wenhui, et al.
Pubblicazione: (2026)

Query-Kontext: An Unified Multimodal Model for Image Generation and Editing
di: Song, Yuxin, et al.
Pubblicazione: (2025)

TexEditor: Structure-Preserving Text-Driven Texture Editing
di: Zhao, Bo, et al.
Pubblicazione: (2026)

Post-hoc and manifold explanations analysis of facial expression data based on deep learning
di: Xiao, Yang
Pubblicazione: (2024)