michaelhodel / arc-dsl
Domain Specific Language for the Abstraction and Reasoning Corpus
☆152Updated last month
Related projects: ⓘ
- Reverse Engineering the Abstraction and Reasoning Corpus☆130Updated last month
- My writings about ARC (Abstraction and Reasoning Corpus)☆55Updated 3 weeks ago
- The history files when recording human interaction while solving ARC tasks☆91Updated this week
- Draw more samples☆159Updated 2 months ago
- Materials for ConceptARC paper☆71Updated 3 months ago
- Language-annotated Abstraction and Reasoning Corpus☆76Updated last year
- Abstract Reasoning with Graph Abstractions (ARGA) implementation☆53Updated 2 months ago
- Multiple datasets for ARC (Abstraction and Reasoning Corpus)☆29Updated this week
- Learning Universal Predictors☆67Updated last month
- The Abstraction and Reasoning Corpus made into a web game☆83Updated 3 weeks ago
- Tools for working with the Abstraction & Reasoning Corpus☆137Updated last month
- Code for 1st place solution to Kaggle's Abstraction and Reasoning Challenge☆132Updated 4 years ago
- Tools for studying developmental interpretability in neural networks.☆69Updated this week
- Like ARC, but code to generate visual puzzles. 1D puzzles first.☆15Updated last month
- Reasoning Computers. Lambda Calculus, Fully Differentiable. Also Neural Stacks, Queues, Arrays, Lists, Trees, and Latches.☆201Updated this week
- Simple Transformer in Jax☆100Updated 2 months ago
- Cost aware hyperparameter tuning algorithm☆95Updated 2 months ago
- seqax = sequence modeling + JAX☆129Updated 2 months ago
- ☆33Updated 3 months ago
- The boundary of neural network trainability is fractal☆155Updated 7 months ago
- Mechanistic Interpretability Visualizations using React☆175Updated 2 months ago
- ☆24Updated 5 months ago
- ☆58Updated this week
- ☆54Updated last week
- ☆53Updated 8 months ago
- Extract full next-token probabilities via language model APIs☆226Updated 6 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆133Updated last month
- MiniHF is an inference, human preference data collection, and fine-tuning tool for local language models. It is intended to help the user…☆143Updated this week
- Scalable neural net training via automatic normalization in the modular norm.☆108Updated 3 weeks ago
- ☆99Updated 10 months ago