Intelligent Visualization of Book Narratives using Natural Language Processing

Structured context augmentation for multimodal LLMs in character art analysis

Structured Creative Evaluation for Text-to-Image Generative AI Models

A multi-dimensional image quality assessment framework for T2I tasks that can not only distinguish overall performance differences across models, but also provide interpretable results at the level of individual dimensions is proposed.

Blending Concepts: Benchmarking Visual Metaphor Generation in Text-to-Image Models

VMetaphor-Bench, the first benchmark for evaluating visual metaphor generation in T2I models, is introduced, combining a multiple-choice question (MCQ) based protocol of 9,594 questions across four levels of metaphorical fidelity with a dimension-based scoring protocol along three perceptual dimensions.

On the Design Fundamentals of Pixel Text Representation Learning

This work investigates the fundamental design principles required for robust visual text representation learning and trains Pixel Linguist II, a native-resolution vision encoder trained with on-the-fly rendering, unified contrastive grounding, and a multilingual curriculum over 280M training examples.

ArCompose: Compositional Text to Image Synthesis for Modern Standard and Iraqi Arabic via Token Supervised Diffusion and NMT Driven Prompt Planning

By using an experimental with controlled single-dataset curriculum on COCO, the structural guidance and curriculum learning were proven to be more than adequate to overcome intricate dialectal and compositional ambiguities in generative AI.

Giraffe: A Mapping Architecture from Hidden Text Representations to Visual Embeddings for Efficient Graphic Design

A novel architecture is proposed that maps hidden token represen- tations to the embedding space of visual models, such as CLIP ViT-L/14, using a single [IMG] token per image.