⚡️ A framework that investigates the scaling limit of ResNets and compares it to Neural ODEs. Tested on synthetic and standardized datasets. 📈
-
Updated
May 27, 2021 - Python
⚡️ A framework that investigates the scaling limit of ResNets and compares it to Neural ODEs. Tested on synthetic and standardized datasets. 📈
[ICML'24] Tackling Prevalent Conditions in Unsupervised Combinatorial Optimization: Cardinality, Minimum, Covering, and More
Research code for heuristically hiding information for inference run on 3rd party systems (ICML 22)
Python package for the ICML 2022 paper "Unsupervised Ground Metric Learning Using Wasserstein Singular Vectors".
🔥OSN in PyTorch (ICML 2024)
The official implementation of the ICML 2023 paper OFQ-ViT
[ICML 2023] Official code for our paper: 'Conditional Tree Matching for Inference-Time Adaptation of Tree Prediction Models'
A repository that implements some proposed methods from popular conference from scratch.
Feature Space Particle Inference for Neural Network Ensembles (ICML2022)
Code for the paper Optimistic Linear Support and Successor Features as a Basis for Optimal Policy Transfer - ICML 2022
T-Basis: a Compact Representation for Neural Networks
Source code of the ICML24 paper "Self-Composing Policies for Scalable Continual Reinforcement Learning" (selected for oral presentation)
Official code for `Visual Attention Emerges from Recurrent Sparse Reconstruction' (ICML 2022)
[ICML'2022] Estimating Instance-dependent Bayes-label Transition Matrix using a Deep Neural Network
Code for the paper Semi-Conditional Normalizing Flows for Semi-Supervised Learning
Community Regularization of Visually Grounded Dialog https://arxiv.org/abs/1808.04359
Official PyTorch implementation of the ICML 2024 paper "Hyperbolic Active Learning for Semantic Segmentation under Domain Shift"
Add a description, image, and links to the icml topic page so that developers can more easily learn about it.
To associate your repository with the icml topic, visit your repo's landing page and select "manage topics."