Cover Image

Rethinking UMM Visual Generation: Masked Modeling for Efficient Image-Only Pre-training

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sun, Peng, Xie, Jun, Lin, Tao
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

ChatUMM: Robust Context Tracking for Conversational Interleaved Generation
by: Dai, Wenxun, et al.
Published: (2026)

Muskie: Multi-view Masked Image Modeling for 3D Vision Pre-training
by: Li, Wenyu, et al.
Published: (2025)

Dataset Ownership Verification for Pre-trained Masked Models
by: Xie, Yuechen, et al.
Published: (2025)

Focus on Texture: Rethinking Pre-training in Masked Autoencoders for Medical Image Classification
by: Madan, Chetan, et al.
Published: (2025)

Efficient Vision-Language Pre-training by Cluster Masking
by: Wei, Zihao, et al.
Published: (2024)

VILA: On Pre-training for Visual Language Models
by: Lin, Ji, et al.
Published: (2023)

LatentUMM: Dual Latent Alignment for Unified Multimodal Models
by: Luo, Yinyi, et al.
Published: (2026)

IRBridge: Solving Image Restoration Bridge with Pre-trained Generative Diffusion Models
by: Wang, Hanting, et al.
Published: (2025)

MaskHOI: Robust 3D Hand-Object Interaction Estimation via Masked Pre-training
by: Xie, Yuechen, et al.
Published: (2025)

MIMIC: Mask Image Pre-training with Mix Contrastive Fine-tuning for Facial Expression Recognition
by: Zhang, Fan, et al.
Published: (2024)

Pan-cancer Histopathology WSI Pre-training with Position-aware Masked Autoencoder
by: Wu, Kun, et al.
Published: (2024)

Effective and Efficient Masked Image Generation Models
by: You, Zebin, et al.
Published: (2025)

Semantics-enhanced Cross-modal Masked Image Modeling for Vision-Language Pre-training
by: Liu, Haowei, et al.
Published: (2024)

Universal Image Restoration Pre-training via Masked Degradation Classification
by: Hu, JiaKui, et al.
Published: (2025)

MaskedCLIP: Bridging the Masked and CLIP Space for Semi-Supervised Medical Vision-Language Pre-training
by: Zhu, Lei, et al.
Published: (2025)

UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation
by: Zhang, Tao, et al.
Published: (2025)

MLIP: Medical Language-Image Pre-training with Masked Local Representation Learning
by: Liu, Jiarun, et al.
Published: (2024)

MiM: Mask in Mask Self-Supervised Pre-Training for 3D Medical Image Analysis
by: Zhuang, Jiaxin, et al.
Published: (2024)

Rethinking Diffusion for Text-Driven Human Motion Generation: Redundant Representations, Evaluation, and Masked Autoregression
by: Meng, Zichong, et al.
Published: (2024)

MaskDiffusion: Exploiting Pre-trained Diffusion Models for Semantic Segmentation
by: Kawano, Yasufumi, et al.
Published: (2024)

From Prototypes to General Distributions: An Efficient Curriculum for Masked Image Modeling
by: Lin, Jinhong, et al.
Published: (2024)

RAW-Adapter: Adapting Pre-trained Visual Model to Camera RAW Images
by: Cui, Ziteng, et al.
Published: (2024)

Emerging Property of Masked Token for Effective Pre-training
by: Choi, Hyesong, et al.
Published: (2024)

Resurrect Mask AutoRegressive Modeling for Efficient and Scalable Image Generation
by: Xin, Yi, et al.
Published: (2025)

Pre-trained Models Succeed in Medical Imaging with Representation Similarity Degradation
by: Zu, Wenqiang, et al.
Published: (2025)

Towards Scalable Pre-training of Visual Tokenizers for Generation
by: Yao, Jingfeng, et al.
Published: (2025)

Boosting Image Restoration via Priors from Pre-trained Models
by: Xu, Xiaogang, et al.
Published: (2024)

Data-efficient Event Camera Pre-training via Disentangled Masked Modeling
by: Huang, Zhenpeng, et al.
Published: (2024)

VTAO-BiManip: Masked Visual-Tactile-Action Pre-training with Object Understanding for Bimanual Dexterous Manipulation
by: Sun, Zhengnan, et al.
Published: (2025)

QPT V2: Masked Image Modeling Advances Visual Scoring
by: Xie, Qizhi, et al.
Published: (2024)

Masks and Manuscripts: Advancing Medical Pre-training with End-to-End Masking and Narrative Structuring
by: Gowda, Shreyank N, et al.
Published: (2024)

Towards Data-Efficient Video Pre-training with Frozen Image Foundation Models
by: Orlova, Svetlana, et al.
Published: (2026)

EVE: Efficient Vision-Language Pre-training with Masked Prediction and Modality-Aware MoE
by: Chen, Junyi, et al.
Published: (2023)

Masked Clustering Prediction for Unsupervised Point Cloud Pre-training
by: Ren, Bin, et al.
Published: (2025)

Masked Pre-training Enables Universal Zero-shot Denoiser
by: Ma, Xiaoxiao, et al.
Published: (2024)

Wavelet-Driven Masked Image Modeling: A Path to Efficient Visual Representation
by: Xiang, Wenzhao, et al.
Published: (2025)

MMCLIP: Cross-modal Attention Masked Modelling for Medical Language-Image Pre-Training
by: Wu, Biao, et al.
Published: (2024)

Rethinking Transformers Pre-training for Multi-Spectral Satellite Imagery
by: Noman, Mubashir, et al.
Published: (2024)

PolarMAE: Efficient Fetal Ultrasound Pre-training via Semantic Screening and Polar-Guided Masking
by: Lv, Meng, et al.
Published: (2026)

RAW-Adapter: Adapting Pre-trained Visual Model to Camera RAW Images and A Benchmark
by: Cui, Ziteng, et al.
Published: (2025)