Jiaxin Zhang's Projects
Uncertainty in Conditional Average Treatment Effect Estimation
Out-of-Distribution Detection Using Layerwise Uncertainty in Deep Neural Networks
Uncertainty Guided Progressive GANs for Medical Image Translation
code and data for the paper: Better Uncertainty Quantification for Machine Translation Evaluation
High-quality implementations of standard and SOTA methods on a variety of tasks.
A python toolbox for predictive uncertainty quantification, calibration, metrics, and visualization
Building blocks for uncertainty-aware cycle consistency presented at NeurIPS'21.
Uncertainty Estimation Using Deep Neural Network and Gradient Boosting Methods
On Uncertainty, Tempering, and Data Augmentation in Bayesian Classification
Code for "Unifying Diffusion Models' Latent Space, with Applications to CycleDiffusion and Guidance"
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
Supplementary material to reproduce "The Unreasonable Effectiveness of Deep Evidential Regression"
Reproducing experimental results of OOD-by-MCD [Yu and Aizawa et al. ICCV 2019]
Uncertainty Quantification 360 (UQ360) is an extensible open-source toolkit that can help you estimate, communicate and use uncertainty in machine learning model predictions.
UQGAN: A Unified Model for Uncertainty Quantification of Deep Classifiers trained via Conditional GANs
UQpy (Uncertainty Quantification with python) is a general purpose Python toolbox for modeling uncertainty in physical and mathematical systems.
Uncertainty-aware Self-training
Code for improved variational Bayesian phylogenetic inference with normalizing flows
code for "VFlow: More Expressive Generative Flows with Variational Data Augmentation"
Implementation of Video Diffusion Models, Jonathan Ho's new paper extending DDPMs to Video Generation - in Pytorch
Code and example dataset for "Variational Disentanglement for Rare Event Modeling"
ICML 21 - Voice2Series: Reprogramming Acoustic Models for Time Series Classification
Vector Quantile Regression
A set of tests for evaluating large-scale algorithms for Wasserstein-2 transport maps computation (NeurIPS 2021)
Code for "Restoring Vision in Adverse Weather Conditions with Patch-Based Denoising Diffusion Models" [arXiv preprint 2207.14626, 2022]
A machine learning benchmark of in-the-wild distribution shifts, with data loaders, evaluators, and default models.
implementation of Wasserstein Natural Policy Gradients