Weilun Feng

Quantized Visual Geometry Grounded Transformer

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

Point-UQ: An Uncertainty-Quantification Paradigm for Point Cloud Few-Shot Class Incremental Learning

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

Geometric Feature Embedding for Effective 3D Few-Shot Class Incremental Learning

Q-VDiT: Towards Accurate Quantization and Distillation of Video-Generation Diffusion Transformers