Jinwoo Kim

tokengt. [NeurIPS'22] Tokenized Graph Transformer (TokenGT), in PyTorch

setvae. [CVPR'21] SetVAE: Learning Hierarchical Composition for Generative Modeling of Set-Structured Data, in PyTorch

hot. [NeurIPS'21] Higher-order Transformers for sets, graphs, and hypergraphs, in PyTorch

ori-giou. GIoU for rotated bounding boxes, vectorized and differentiable

ehnn. [ECCV'22] Equivariant Hypergraph Neural Networks, in PyTorch

lps. [NeurIPS'23 Spotlight] Learning Probabilistic Symmetrization for Architecture Agnostic Equivariance (LPS), in PyTorch

random-walk. [ICLR'25 Spotlight] Revisiting Random Walks for Learning on Graphs (RWNN), in PyTorch

flock. [ICLR'26] Flock: A Knowledge Graph Foundation Model via Learning on Random Walks, in PyTorch

spectral-mean-flow. [NeurIPS'25] Sequence Modeling with Spectral Mean Flows, in PyTorch

tied. [arXiv'26] Inverting Data Transformations via Diffusion Sampling, in PyTorch

emlp-pytorch. A PyTorch port of EMLP JAX library (Finzi et al. 2021)