top-quarks / ARC-solutionLinks
Code for 1st place solution to Kaggle's Abstraction and Reasoning Challenge
☆163Updated 4 months ago
Alternatives and similar repositories for ARC-solution
Users that are interested in ARC-solution are comparing it to the libraries listed below
Sorting:
- Tools for working with the Abstraction & Reasoning Corpus☆212Updated 3 months ago
- Domain Specific Language for the Abstraction and Reasoning Corpus☆313Updated last year
- Reverse Engineering the Abstraction and Reasoning Corpus☆319Updated 9 months ago
- Abstract Reasoning with Graph Abstractions (ARGA) implementation☆61Updated last year
- Materials for ConceptARC paper☆108Updated last year
- The Abstraction and Reasoning Corpus made into a web game☆90Updated last year
- Language-annotated Abstraction and Reasoning Corpus☆98Updated 2 years ago
- My writings about ARC (Abstraction and Reasoning Corpus)☆86Updated last month
- The history files when recording human interaction while solving ARC tasks☆118Updated 3 weeks ago
- Multiple datasets for ARC (Abstraction and Reasoning Corpus)☆84Updated 8 months ago
- Draw more samples☆195Updated last year
- Latent Program Network (from the "Searching Latent Program Spaces" paper)☆106Updated last week
- Our solution for the arc challenge 2024☆185Updated 5 months ago
- Neural Networks and the Chomsky Hierarchy☆211Updated last year
- ☆201Updated 3 months ago
- Solving the Abstraction & Reasoning Corpus with DreamCoder☆53Updated last year
- Create an AI capable of solving reasoning tasks it has never seen before☆96Updated 11 months ago
- Bootstrapping ARC☆150Updated last year
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆130Updated 3 years ago
- A Gymnasium-based Environment of the Abstraction and Reasoning Corpus (ARC)☆69Updated last year
- Tools for studying developmental interpretability in neural networks.☆117Updated 5 months ago
- Learning Universal Predictors☆81Updated last year
- Scaling scaling laws with board games.☆54Updated 2 years ago
- ☆46Updated 3 years ago
- unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"☆79Updated 3 years ago
- Brain-Inspired Modular Training (BIMT), a method for making neural networks more modular and interpretable.☆174Updated 2 years ago
- ☆73Updated 3 years ago
- ☆540Updated 2 years ago
- Emergent world representations: Exploring a sequence model trained on a synthetic task☆191Updated 2 years ago
- Implementing RASP transformer programming language https://arxiv.org/pdf/2106.06981.pdf.☆58Updated last month