Andreas Kirsch

tfpyth. Putting TensorFlow back in PyTorch, back in TensorFlow (differentiable TensorFlow PyTorch adapters).

toma. Helps you write algorithms in PyTorch that adapt to the available (CUDA) memory

llm-strategy. Directly Connecting Python to LLMs via Strongly-Typed Functions, Dataclasses, Interfaces & Generic Types

BatchBALD. Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning.

neural_net_checklist. Python

dart_repl. Proof of concept REPL shell for Dart

batchbald_redux. Reusable BatchBALD implementation

mdp. Make it easy to specify simple MDPs that are compatible with the OpenAI Gym.

mnist_by_zip. Compression algorithms (like the well-known zip file compression) can be used for machine learning purposes, specifically for classifying hand-written digits (MNIST)

llmtracer. Trace LLM calls (and others) and visualize them in WandB, as interactive SVG or using a streaming local webapp

chatplayground. Chat Playground for LLMs

player_of_jeopardy. ChatGPT can solve Jeopardy! clues really well!

ddu_dirty_mnist. Dirty-MNIST dataset introduced in "Deterministic Neural Networks with Inductive Biases Capture Epistemic and Aleatoric Uncertainty" (https://arxiv.org/abs/2102.11582)

pbt. Jupyter notebooks to play around with population based training, as described in https://arxiv.org/abs/1711.09846

2302.08981. Jupyter Notebook

blackboard-pagi. Python

pytorch_datadiet. Python

batch_pong_poc. Instead of running one environment at a time or one per thread, run everything in batch using numpy on a single core.

hello-slurm. Shell

implicit_lambda. This package adds support for implicit lambdas, so you can write `map(_ + 5, a_list)` instead of `map(lambda x: x + 5, a_list)`.

fauxpilot. FauxPilot - an open-source GitHub Copilot server

laaos. Logs as append-only source.

lean-codex-formalization. Lean

dart_metamath_naive. Naive/shoddy implementation of MetaMath in Dart

active-bayesian-coresets. Jupyter Notebook

o1-replication-journey-tree-viewer. Python

SFML. Simple and Fast Multimedia Library

algo_fairness. Jupyter Notebook

uncertainty-metrics. An easy-to-use interface for measuring uncertainty and robustness.

WML. Whitespace Markup Language

iclr_2024_blog_post. HTML

readme2tex. Renders TeXy Math for Github Readmes

iot-river-crossing-codex. Python

active_learning_redux. Python

aims_lab. Jupyter Notebook

ordl. Open Research and Derivatives License (ORDL)

data_diet. Jupyter Notebook

2020_ebm_presentation. A presentation about EBMs and Hopfield networks @ OATML

iot-river-crossing-jules. Python

uncertainty-baselines. High-quality implementations of standard and SOTA methods on a variety of tasks.

2409.02628. (Implicit) Ensembles of Ensembles: Epistemic Uncertainty Collapse in Large Models

2202.01851. Repository for 'A Note on "Assessing Generalization of SGD via Disagreement"'

angular.dart. A web framework for Dart

2208.00549. Unifying Approaches in Data Subset Selection - Experiments

dlb_chapter2. TeX