赵荣臻 Zhao, Rongzhen

SAVi-PyTorch. SAVi -- Unofficial But 3x Faster Training @ Better Performance. Implementation of ICLR 2022 Paper "Conditional Object-Centric Learning from Video".

ConvolutionOfConvolution. Source code of CVPR'22 paper "Convolution of Convolution: Let Kernels Spatially Collaborate".

VQ-VFM-OCL. Vector-Quantized Vision Foundation Models for Object-Centric Learning, ACM MM 2025.

SmoothSA. Smoothing Slot Attention Iterations and Recurrences, ICML 2026.

MultiScaleFusion. Multi-Scale Fusion for Object Representation, ICLR 2025.

RandSF.Q. Predicting Video Slot Attention Queries from Random Slot-Feature Pairs, AAAI 2026.

LearnableHeterogeneousConvolution. Source code of paper "Learnable Heterogeneous Convolution: Learning both topology and strength".

DIAS. Slot Attention with Re-Initialization and Self-Distillation, ACM MM 2025.

GroupedDiscreteRepresentation. Grouped Discrete Representation for Object-Centric Learning, ECML 2025