Skip to content

Training Experiment · Jupyter Notebook

arc-vit

Experiments with ViT and ARC

What it is

The repository provides tools for loading and visualizing ARC tasks, along with experiments training convolutional autoencoders on ARC data using different input representations (one-hot, color_xy, normalized). It focuses on representation learning via autoencoding rather than solving the ARC prediction task.

Scored at332a52a14 Nov 2026Changes since

Merit describes the code at this commit. Later pushes count once the owner rescans. How merit is scored

Distribution based on AI work

1 / 2
Machine Learning: 50.0%Computer Vision: 33.3%Data Science: 16.7%
  • Machine Learning50%
  • Computer Vision33%
  • Data Science17%

Each field's share of the project's AI work, as scoring counts it. It ranks in the field it is most about.

What the judge found

Read from the project's code at its scored commit.

Strengths3

  • Modular and reusable code for ARC data loading and visualization.
  • Well-documented helper functions (e.g., color_xy.py) with clear docstrings.
  • Notebooks demonstrate executed training runs and show qualitative results.

Limitations

The owner keeps this project's limitations private.

Around it on the Machine Learning board

Whole board
  1. 115, shared rankSafe-HomeML Application · HTML47.5/100ImplementationIrine Milton
  2. 115, shared ranksimon-arc-lab-legacyEducational Implementation · Jupyter Notebook47.5/100ImplementationSimon Strandgaard
  3. 117, shared rankLSIS-ISLML Application · Jupyter Notebook47.3/100ImplementationKashish gupta
  4. 117, shared rankarc-vitTraining Experiment · Jupyter Notebook47.3/100ImplementationSimon Strandgaard
  5. 119mnist-digit-recognitionML Application · Python46.8/100ImplementationMohamed Khayat

More from Simon Strandgaard