Skip to content
@bethgelab

Bethge Lab

Perceiving Neural Networks

Pinned Loading

  1. foolbox foolbox Public

    A Python toolbox to create adversarial examples that fool neural networks in PyTorch, TensorFlow, and JAX

    Python 2.9k 435

  2. CiteME CiteME Public

    CiteME is a benchmark designed to test the abilities of language models in finding papers that are cited in scientific texts.

    Python 48 5

  3. model-vs-human model-vs-human Public

    Benchmark your model on out-of-distribution datasets with carefully collected human comparison data (NeurIPS 2021 Oral)

    Python 358 54

  4. robust-detection-benchmark robust-detection-benchmark Public

    Code, data and benchmark from the paper "Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming" (NeurIPS 2019 ML4AD)

    Jupyter Notebook 191 24

  5. imagecorruptions imagecorruptions Public

    Python package to corrupt arbitrary images.

    Python 458 72

  6. stylize-datasets stylize-datasets Public

    A script that applies the AdaIN style transfer method to arbitrary datasets

    Python 165 38

Repositories

Showing 10 of 48 repositories
  • foolbox Public

    A Python toolbox to create adversarial examples that fool neural networks in PyTorch, TensorFlow, and JAX

    bethgelab/foolbox’s past year of commit activity
    Python 2,935 MIT 435 23 (1 issue needs help) 6 Updated Dec 3, 2025
  • what-moves-the-eyes Public

    Project page for "What Moves the Eyes: Doubling Mechanistic Model Performance Using Deep Networks to Discover and Test Cognitive Hypotheses"

    bethgelab/what-moves-the-eyes’s past year of commit activity
    Python 0 MIT 0 0 0 Updated Nov 30, 2025
  • supersanity Public

    A critical analysis of the Cambrian-S model and VSI-Super benchmarks

    bethgelab/supersanity’s past year of commit activity
    Python 11 MIT 0 2 0 Updated Nov 20, 2025
  • sober-reasoning Public

    A Sober Look at Language Model Reasoning

    bethgelab/sober-reasoning’s past year of commit activity
    HTML 92 5 5 0 Updated Nov 18, 2025
  • CiteME Public

    CiteME is a benchmark designed to test the abilities of language models in finding papers that are cited in scientific texts.

    bethgelab/CiteME’s past year of commit activity
    Python 48 5 0 0 Updated Nov 3, 2025
  • onebench Public

    [ACL'25] The official code for "ONEBench to Test Them All: Sample-Level Benchmarking Over Open-Ended Capabilities"

    bethgelab/onebench’s past year of commit activity
    Python 5 MIT 0 0 0 Updated Jul 29, 2025
  • imagecorruptions Public

    Python package to corrupt arbitrary images.

    bethgelab/imagecorruptions’s past year of commit activity
    Python 458 Apache-2.0 72 3 1 Updated May 6, 2025
  • model-vs-human Public

    Benchmark your model on out-of-distribution datasets with carefully collected human comparison data (NeurIPS 2021 Oral)

    bethgelab/model-vs-human’s past year of commit activity
    Python 358 54 3 0 Updated Apr 17, 2025
  • sort-and-search Public

    Code for the paper: "Efficient Lifelong Model Evaluation in an Era of Rapid Progress" [NeurIPS'24]

    bethgelab/sort-and-search’s past year of commit activity
    Python 10 2 0 0 Updated Oct 17, 2024
  • frequency_determines_performance Public

    Code for the paper: "No Zero-Shot Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance" [NeurIPS'24]

    bethgelab/frequency_determines_performance’s past year of commit activity
    Jupyter Notebook 93 MIT 4 1 0 Updated Apr 29, 2024

Top languages

Loading…

Most used topics

Loading…