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.