Inconsistencies In Consistency Models: Better ODE Solving Does Not Imply Better Samples

TabDPT: Scaling Tabular Foundation Models

Text-2-SQL

Evaluating fairness of conformal prediction with human interaction

Manifold-aware deep generative models for calorimeter simulation.

A framework for providing certified robustness guarantees with differentially private models

Codebase for benchmarking robustness of Self-Supervised Learning across diverse downstream tasks

A scalable implementation of diffusion and flow-matching with XGBoost models, applied to calorimeter data.

Python package for conformal prediction

A Python toolbox for conformal prediction research on deep learning models, using PyTorch.

A Python package for intrinsic dimension estimation

Human in the Loop Conformal Prediction

Data-Efficient Multimodal Fusion on a Single GPU

Code for the ICLR'24 paper "Self-supervised Representation Learning From Random Data Projectors

Generating and Imputing Tabular Data via Diffusion and Flow XGBoost Models

Code accompanying the paper "Disparate Impact in Differential Privacy from Gradient Misalignment".

Codebase for evaluation of deep generative models as presented in Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models

Code for the NeurIPS'21 paper "Tractable Density Estimation on Learned Manifolds with Conformal Embedding Flows"

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

Code accompanying the paper "Decentralized Federated Learning through Proxy Model Sharing"

Codebase accompanying the paper "Diagnosing and Fixing Manifold Overfitting in Deep Generative Models"