Cover Image

Do Text Edits Generalize to Visual Generation? Benchmarking Cross-Modal Knowledge Editing in UMMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Gao, Xin, Yang, Cheng, Shi, Chufan, Berg-Kirkpatrick, Taylor
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Are VLMs Seeing or Just Saying? Uncovering the Illusion of Visual Re-examination
by: Shi, Chufan, et al.
Published: (2026)

From Reasoning to Pixels: Benchmarking the Alignment Gap in Unified Multimodal Models
by: Yang, Cheng, et al.
Published: (2026)

Optical Context Compression Is Just (Bad) Autoencoding
by: Lee, Ivan Yee, et al.
Published: (2025)

Visual-RAG: Benchmarking Text-to-Image Retrieval Augmented Generation for Visual Knowledge Intensive Queries
by: Wu, Yin, et al.
Published: (2025)

TextInVision: Text and Prompt Complexity Driven Visual Text Generation Benchmark
by: Fallah, Forouzan, et al.
Published: (2025)

Alt-Text with Context: Improving Accessibility for Images on Twitter
by: Srivatsan, Nikita, et al.
Published: (2023)

LogogramNLP: Comparing Visual and Textual Representations of Ancient Logographic Writing Systems for NLP
by: Chen, Danlu, et al.
Published: (2024)

ChartMimic: Evaluating LMM's Cross-Modal Reasoning Capability via Chart-to-Code Generation
by: Yang, Cheng, et al.
Published: (2024)

MULTITEXTEDIT: Benchmarking Cross-Lingual Degradation in Text-in-Image Editing
by: Cheng, Liwei, et al.
Published: (2026)

Exploring Typographic Visual Prompts Injection Threats in Cross-Modality Generation Models
by: Cheng, Hao, et al.
Published: (2025)

VEFX-Bench: A Holistic Benchmark for Generic Video Editing and Visual Effects
by: Gao, Xiangbo, et al.
Published: (2026)

MC-MKE: A Fine-Grained Multimodal Knowledge Editing Benchmark Emphasizing Modality Consistency
by: Zhang, Junzhe, et al.
Published: (2024)

VCG-Bench: Towards A Unified Visual-Centric Benchmark for Structured Generation and Editing
by: Su, Xiaoyan, et al.
Published: (2026)

Cross-Modal Retrieval for Motion and Text via DropTriple Loss
by: Yan, Sheng, et al.
Published: (2023)

MotionEdit: Benchmarking and Learning Motion-Centric Image Editing
by: Wan, Yixin, et al.
Published: (2025)

Text2Vis: A Challenging and Diverse Benchmark for Generating Multimodal Visualizations from Text
by: Rahman, Mizanur, et al.
Published: (2025)

ControlEdit: A MultiModal Local Clothing Image Editing Method
by: Cheng, Di, et al.
Published: (2024)

Text-to-Image Cross-Modal Generation: A Systematic Review
by: Żelaszczyk, Maciej, et al.
Published: (2024)

Attribution Analysis Meets Model Editing: Advancing Knowledge Correction in Vision Language Models with VisEdit
by: Chen, Qizhou, et al.
Published: (2024)

ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation
by: Yuan, Shenghai, et al.
Published: (2024)

Visually Guided Generative Text-Layout Pre-training for Document Intelligence
by: Mao, Zhiming, et al.
Published: (2024)

SeedEdit 3.0: Fast and High-Quality Generative Image Editing
by: Wang, Peng, et al.
Published: (2025)

SeedEdit: Align Image Re-Generation to Image Editing
by: Shi, Yichun, et al.
Published: (2024)

Bilingual Text-to-Motion Generation: A New Benchmark and Baselines
by: Weng, Wanjiang, et al.
Published: (2026)

Enhancing Chest X-ray Classification through Knowledge Injection in Cross-Modality Learning
by: Yan, Yang, et al.
Published: (2025)

Precision or Recall? An Analysis of Image Captions for Training Text-to-Image Generation Model
by: Cheng, Sheng, et al.
Published: (2024)

InstructEdit: Instruction-based Knowledge Editing for Large Language Models
by: Zhang, Ningyu, et al.
Published: (2024)

Knowledge Visualization: A Benchmark and Method for Knowledge-Intensive Text-to-Image Generation
by: Zhao, Ran, et al.
Published: (2026)

Unraveling Cross-Modality Knowledge Conflicts in Large Vision-Language Models
by: Zhu, Tinghui, et al.
Published: (2024)

MMMG: A Massive, Multidisciplinary, Multi-Tier Generation Benchmark for Text-to-Image Reasoning
by: Luo, Yuxuan, et al.
Published: (2025)

Benchmarking and Enhancing Text-to-Image Models for Generating Visual Representations in Early Arithmetic Education
by: Wang, Junling, et al.
Published: (2026)

Edit-Compass & EditReward-Compass: A Unified Benchmark for Image Editing and Reward Modeling
by: Bai, Xuehai, et al.
Published: (2026)

OmniParser V2: Structured-Points-of-Thought for Unified Visual Text Parsing and Its Generality to Multimodal Large Language Models
by: Yu, Wenwen, et al.
Published: (2025)

R2I-Bench: Benchmarking Reasoning-Driven Text-to-Image Generation
by: Chen, Kaijie, et al.
Published: (2025)

M$^3$Face: A Unified Multi-Modal Multilingual Framework for Human Face Generation and Editing
by: Mofayezi, Mohammadreza, et al.
Published: (2024)

AnyText: Multilingual Visual Text Generation And Editing
by: Tuo, Yuxiang, et al.
Published: (2023)

CEIDM: A Controlled Entity and Interaction Diffusion Model for Enhanced Text-to-Image Generation
by: Yang, Mingyue, et al.
Published: (2025)

Do we Really Need Visual Instructions? Towards Visual Instruction-Free Fine-tuning for Large Vision-Language Models
by: Liu, Zikang, et al.
Published: (2025)

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

VisRet: Visualization Improves Knowledge-Intensive Text-to-Image Retrieval
by: Wu, Di, et al.
Published: (2025)