EditMGT applies masked generative transformers with attention consolidation and region-hold sampling to deliver state-of-the-art localized image editing at 6x the speed of diffusion methods.
arXiv preprint arXiv:2508.15772 (2025)
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 2
baseline 2
citation-polarity summary
fields
cs.CV 6years
2026 6verdicts
UNVERDICTED 6representative citing papers
A co-trained adapter framework enables mask-free local editing in DiTs by factorizing edit semantics from spatial location and jointly learning a mask predictor.
UniEditBench unifies image and video editing evaluation with a nine-plus-eight operation taxonomy and cost-effective 4B/8B distilled MLLM evaluators that align with human judgments.
A pixel-space Diffusion Transformer with Unified Transformer architecture unifies image generation, editing, and personalization in an end-to-end model that maps all inputs to a shared token space and scales from 8B to over 200B parameters.
Visual generation models are evolving from passive renderers to interactive agentic world modelers, but current systems lack spatial reasoning, temporal consistency, and causal understanding, with evaluations overemphasizing perceptual quality.
This review organizes literature on large multimodal models and object-centric vision into four themes—understanding, referring segmentation, editing, and generation—while summarizing paradigms, strategies, and challenges like instance permanence and consistent interaction.
citing papers explorer
-
Masked Generative Transformer Is What You Need for Image Editing
EditMGT applies masked generative transformers with attention consolidation and region-hold sampling to deliver state-of-the-art localized image editing at 6x the speed of diffusion methods.
-
Edit Where You Mean: Region-Aware Adapter Injection for Mask-Free Local Image Editing
A co-trained adapter framework enables mask-free local editing in DiTs by factorizing edit semantics from spatial location and jointly learning a mask predictor.
-
UniEditBench: A Unified and Cost-Effective Benchmark for Image and Video Editing via Distilled MLLMs
UniEditBench unifies image and video editing evaluation with a nine-plus-eight operation taxonomy and cost-effective 4B/8B distilled MLLM evaluators that align with human judgments.
-
HiDream-O1-Image: A Natively Unified Image Generative Foundation Model with Pixel-level Unified Transformer
A pixel-space Diffusion Transformer with Unified Transformer architecture unifies image generation, editing, and personalization in an end-to-end model that maps all inputs to a shared token space and scales from 8B to over 200B parameters.
-
Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling
Visual generation models are evolving from passive renderers to interactive agentic world modelers, but current systems lack spatial reasoning, temporal consistency, and causal understanding, with evaluations overemphasizing perceptual quality.
-
LMMs Meet Object-Centric Vision: Understanding, Segmentation, Editing and Generation
This review organizes literature on large multimodal models and object-centric vision into four themes—understanding, referring segmentation, editing, and generation—while summarizing paradigms, strategies, and challenges like instance permanence and consistent interaction.