Ran Yi

LayerSVG: Layer-wise Semantic Editable Scalable Vector Graphics Synthesis

OmniCustom: A Multimodal-Driven Architecture for Customized Video Generation

MesaTask: Towards Task-Driven Tabletop Scene Generation via 3D Spatial Reasoning

PolyVivid: Vivid Multi-Subject Video Generation with Cross-Modal Interaction and Enhancement

WaveAR: Wavelet-Aware Continuous Autoregressive Diffusion for Accurate Human Motion Prediction

SaRA: High-Efficient Diffusion Model Fine-tuning with Progressive Sparse Low-Rank Adaptation

MV-Adapter: Multi-view Consistent Image Generation Made Easy

High-fidelity and realtime 3D Gaussian Head Avatars with Expressive and Compact blenshape representations

Textual $D$ecomposition then Sub-motion-space $S$cattering for $O$pen-Vocabulary Motion Generation

Real&Synthetic Dataset and the Linear Attention in Image Restoration

Rectified Diffusion Guidance for Conditional Generation