Introducing TextImage Augmentation for Document Images

Training Design for Text-to-Image Models: Lessons from Ablations

VDE Bench: Evaluating The Capability of Image Editing Models to Modify Visual Documents

arXiv:2602. 00122v3 Announce Type: replace-cross Abstract: In recent years, image editing models have made significant progress, enabling users to manipulate visual content in a flexible and interactive manner through natural language instructions.

Introducing ChatGPT Images 2.0

ChatGPT Images 2. 0 introduces a state-of-the-art image generation model with improved text rendering, multilingual support, and advanced visual reasoning.

Welcome aMUSEd: Efficient Text-to-Image Generation

Failure-Informed Image Self-Augmentation for Multimodal Large Language Model Self-Improvement

arXiv:2608. 03733v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have achieved remarkable performance across vision-language tasks, but their progress depends heavily on large-scale, high-quality multimodal data that are costly to annotate.

Failure-Informed Image Self-Augmentation for Multimodal Large Language Model Self-Improvement

Multimodal large language models (MLLMs) have achieved remarkable performance across vision-language tasks, but their progress depends heavily on large-scale, high-quality multimodal data that are costly to annotate. Self-augmentation offers a promising alternative by enabling models to expand their own training data without external supervision.

Seeing is Believing: Aligning Prompt Rewriting with Visual Anchors for Text-to-Image Generation

arXiv:2606. 08492v1 Announce Type: cross Abstract: Despite the impressive capabilities of text-to-image (T2I) models, an intent-generation gap often persists due to the brevity and ambiguity of user prompts.

NaviDC-OCR: Navigating Document Parsing Across Digital and Camera-Captured Documents

arXiv:2608. 12898v1 Announce Type: cross Abstract: Document parsing aims to transform unstructured documents into structured and machine-readable representations.

Accelerating Document AI

TextRefine: Improving Textual Fidelity, Spatial Placement, and Glyph Rendering for Text Editing in Product Posters

arXiv:2608. 19637v1 Announce Type: new Abstract: Text editing in product posters entails inserting new text or replacing existing text while preserving product appearance, background content, and global composition.

Open Preference Dataset for Text-to-Image Generation by the 🤗 Community

TextRefine: Improving Textual Fidelity, Spatial Placement, and Glyph Rendering for Text Editing in Product Posters

Text editing in product posters entails inserting new text or replacing existing text while preserving product appearance, background content, and global composition. Despite recent progress in instruction-based image editing, general-purpose models remain unreliable in this setting: they often omit or incorrectly render the target text, place it over salient products or pre-existing content, and produce structurally distorted or visually inconsistent glyphs.