This is a collection of our zero-cost NAS and efficient vision applications.

Unity's privacy-preserving human-centric synthetic data generator

Official Pytorch code for Structure-Aware Transformer.

Official implementation of "Multi-Task Learning as a Bargaining Game" [ICML 2022]

PyTorch code for the RetoMaton paper: "Neuro-Symbolic Language Modeling with Automaton-augmented Retrieval" (ICML 2022)

[ICML 2022]Source code for "A Closer Look at Smoothness in Domain Adversarial Training",

[ICML 2022] Latent Diffusion Energy-Based Model for Interpretable Text Modeling

GraphCON (ICML 2022)

[ICML 2022] "ProGCL: Rethinking Hard Negative Mining in Graph Contrastive Learning"

Code for the paper "Showing Your Offline Reinforcement Learning Work: Online Evaluation Budget Matters", ICML 2022

[ICML 2022] Conditional GANs with Auxiliary Discriminative Classifier

[ICML2022] Variational Wasserstein gradient flow

DETRtime, a framework for time-series segmentation

Official pytorch code for "APP: Anytime Progressive Pruning" (DyNN @ ICML, 2022; CLL @ ACML, 2022, SNN @ ICML, 2022 and SlowDNN 2023)

"Learning Stable Classifiers by Transferring Unstable Features" ICML 2022

Python package for the ICML 2022 paper "Unsupervised Ground Metric Learning Using Wasserstein Singular Vectors".

The original PyTorch implementation of the "EXACT: How Train Your Accuracy"

[ICML22] Balancing Discriminability and Transferability for Source-Free Domain Adaptation

Code for Double Sampling Randomized Smoothing [ICML 2022]