Yue Ma

FastVMT: Eliminating Redundancy in Video Motion Transfer

HiCache: A Plug-in Scaled-Hermite Upgrade for Taylor-Style Cache-then-Forecast Diffusion Acceleration

EVCtrl: Efficient Control Adapter for Visual Generation

Follow-Your-Shape: Shape-Aware Image Editing via Trajectory-Guided Region Control

Multi-Layer Diffusion Strategy for Multi-IP Interaction-Aware Human Erasing

EffiVMT: Video Motion Transfer via Efficient Spatial-Temporal Decoupled Finetuning

EasyCreator: Empowering 4D Creation through Video Inpainting

SkipVAR: Accelerating Visual Autoregressive Modeling via Adaptive Frequency-Aware Skipping

DiTraj: Training-free Trajectory Control For Video Diffusion Transformer

Z-Cache: Accelerating Diffusion Transformers via Self-Reflection

InstanceAnimator: Multi-Instance Sketch Video Colorization

Scale-Adapter: Reversed Distillation Adapter for Efficient Training of Large Video Diffusion Models

GR-Gaussian: Graph-Based Radiative Gaussian Splatting for Sparse-View Tomographic Reconstruction

Egocentric Cross-Embodiment Video Editing via Dual Contrastive Representation Learning

Taming Rectified Flow for Inversion and Editing

InstantSwap: Fast Customized Concept Swapping across Sharp Shape Differences

Towards Multiple Character Image Animation Through Enhancing Implicit Decoupling