-
Carnegie Mellon University
Stars
Proximal Policy Optimization (Continuous Version) in PyTorch.
Code for the paper "Evolution Strategies as a Scalable Alternative to Reinforcement Learning"
Seamless operability between C++11 and Python
[NeurIPS 2025] Latent Zoning Networks
A high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.
shuqike / openfmri
Forked from poldrack/openfmricode related to the OpenFMRI project
shuqike / glasser360
Forked from brainspaces/glasser360360-node volumetric atlas derived from the multimodal parcellation from Glasser and colleagues
shuqike / pyrcc
Forked from yhenon/pyrccPython implementation of Robust Continuous Clustering
3.8% and 18.3% on CIFAR-10 and CIFAR-100
shuqike / pytorch-privacy
Forked from ebagdasa/pytorch-privacysimple Differential Privacy in PyTorch
shuqike / DataShapley
Forked from amiratag/DataShapleyData Shapley: Equitable Valuation of Data for Machine Learning
Efficient Computation and Analysis of Distributional Shapley Values (AISTATS 2021)
Distributional Shapley: A Distributional Framework for Data Valuation
Wide Residual Networks (WideResNets) in PyTorch
shuqike / auditing-dpsgd
Forked from jagielski/auditing-dpsgdCode for Auditing DPSGD
shuqike / GFdynamics
Forked from eboursier/GFdynamicsCode used for "Gradient flow dynamics of shallow ReLU networks for square loss and orthogonal inputs"
shuqike / leap
Forked from snasiriany/leapOfficial codebase for LEAP: Planning with Goal Conditioned Policies
1000 images, one per image-net class. For easy visualization/exploration of classes.
shuqike / beta_shapley
Forked from ykwon0407/beta_shapleyBeta Shapley: a Unified and Noise-reduced Data Valuation Framework for Machine Learning (AISTATS 2022 Oral)
Learning to See by Looking at Noise
shuqike / MC-Simulator
Forked from CraftJarvis/MC-SimulatorA modified version of MineDojo
Code and data for Katsumi et al., in press, "Correspondence of functional connectivity gradients across human isocortex, cerebellum, and hippocampus".
Here is a Google Colab Notebook for fine-tuning Alpaca Lora (within 3 hours with a 40GB A100 GPU)