rankseg-series

Boost segmentation model mIoU/Dice instantly WITHOUT retraining. A plug-and-play, training-free optimization module. Published in NeurIPS & JMLR. Compatible with SAM, DeepLab, SegFormer, and more. 🧩

ensLoss_full

[ICML2025] EnsLoss: Stochastic Calibrated Loss Ensembles for Preventing Overfitting in Classification

ensLoss_mini

[ICML2025] EnsLoss: Stochastic Calibrated Loss Ensembles for Preventing Overfitting in Classification

wMMD

Word-Level Maximum Mean Discrepancy Regularization for Word Embedding

nl-causal

[CLeaR2024] Inference of Nonlinear Causal Effects with Application to TWAS with GWAS Summary Data

rehline_full

[NeurIPS2023] Regularized Composite ReLU-ReHU Loss Minimization with Linear Computation and Linear Convergence

rehline_mini

[NeurIPS2023] Regularized Composite ReLU-ReHU Loss Minimization with Linear Computation and Linear Convergence

ncd

dnn-locate

rankseg

dnn-inference

beamer