Yuqi Li

Quantized Visual Geometry Grounded Transformer

QuantSparse: Comprehensively Compressing Video Diffusion Transformer with Model Quantization and Attention Sparsification

Equivariant Graph Neural ODEs for Modeling Physical Dynamics

Reinforcing Spatio-Temporal Graph Neural Networks with a Physics Reward Oracle

$\text{S}^2$Q-VDiT: Accurate Quantized Video Diffusion Transformer with Salient Data and Sparse Token Distillation