This is the code for the paper "Revisiting Reweighted Risk for Calibration: AURC, Focal Loss, and Inverse Focal Loss".

Classification metrics and post-hoc calibration

Codebase for "Optimizing Estimators of Squared Calibration Errors in Classification", published at TMLR

Codebase for "Disentangling Mean Embeddings for Better Diagnostics of Image Generators", published at IAI Workshop @ NeurIPS 2024.

Codebase for "A Bias-Variance-Covariance Decomposition of Kernel Scores for Generative Models", published at ICML 2024.

State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and performance on enterprise-grade infrastructure.

Persian/Farsi text to speech(TTS) training using coqui tts

BA Project Moritz Schwerdt, Interpretation of SKCE

This is a curated list for Information Bottleneck Principle, in memory of Professor Naftali Tishby.

A curated list of practical guide resources of LLMs (LLMs Tree, Examples, Papers)

A multi-view latent variable model with domain-informed structured sparsity for integrating noisy feature sets.

The official source code to: Uncertainty Estimates of Predictions via a General Bias-Variance Decomposition (AISTATS'23)

A markup-based typesetting system that is powerful and easy to learn.

The official source code to: Better Uncertainty Calibration via Proper Scores for Classification and Beyond (NeurIPS'22)

Corruption and Perturbation Robustness (ICLR 2019)

🔺 Ternary plotting library for python with matplotlib

Acceptance rates for the major AI conferences

Sioyek is a PDF viewer with a focus on textbooks and research papers

The net:cal calibration framework is a Python 3 library for measuring and mitigating miscalibration of uncertainty estimates, e.g., by a neural network.

my PhD thesis on Bayesian inference

parallel graph management and execution in heterogeneous computing

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

A Bayesian Analysis Toolkit in Julia

This plugin displays your tex source in a textarea so plugins like grammarly can check it.

Official Pytorch implementation of the preprint paper "Castle in the Sky: Dynamic Sky Replacement and Harmonization in Videos", in arXiv:2010.11800.

NVIDIA's Deep Imagination Team's PyTorch Library

A Vim-like interface for Firefox, inspired by Vimperator/Pentadactyl.

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

💦 Seamless, distributed, real-time integration of Blender into PyTorch data pipelines

Tools and libraries to run neural networks in Minecraft ⛏️