The Lottery Ticket Hypothesis in Denoising: Towards Semantic-Driven Initialization

LayoutFlow: Flow Matching for Layout Generation

Retrieval-Augmented Layout Transformer for Content-Aware Layout Generation

Makeup Prior Models for 3D Facial Makeup Estimation and Applications

SuperNormal: Neural Surface Reconstruction via Multi-View Normal Integration

Towards Diverse and Consistent Typography Generation

Complementary-Contradictory Feature Regularization against Multimodal Overfitting

Multimodal color recommendation in vector graphic documents

Dissecting multimodal learning via regularized masking of multimodal features

グラフィックデザインの教師ありレイヤー分解

Text-to-Image手法を使用した広告画像生成と構図提案

iMixer: invertible, implicit, and iterative MLP-Mixer from modern Hopfield networks

LayoutDM: Discrete Diffusion Model for Controllable Layout Generation

Towards Flexible Multi-modal Document Models

Color Recommendation for Vector Graphic Documents based on Multi-Palette Representation

Contrastive Losses Are Natural Criteria for Unsupervised Video Summarization

AxIoU: An Axiomatically Justified Measure for Video Moment Retrieval

Towards Universal Multi-Modal Layout Models

An Intelligent Color Recommendation Tool for Landing Page Design

Optimal Correction Cost for Object Detection Evaluation

Does robustness on ImageNet transfer to downstream tasks?