agemoai / arcsolverLinks
A Python library for automatically solving Abstraction and Reasoning Corpus (ARC) challenges using Claude and object-centric modeling.
☆23Updated 8 months ago
Alternatives and similar repositories for arcsolver
Users that are interested in arcsolver are comparing it to the libraries listed below
Sorting:
- slowly building a set of infinite riddle generators for data-hungry methods☆14Updated 2 years ago
- ☆100Updated 8 months ago
- MiniHF is an inference, human preference data collection, and fine-tuning tool for local language models. It is intended to help the user…☆180Updated 2 months ago
- Probabilistic LLM evaluations. [CogSci2023; ACL2023]☆73Updated last year
- Like ARC, but code to generate visual puzzles. 1D puzzles first.☆21Updated last year
- Materials for ConceptARC paper☆102Updated 10 months ago
- Draw more samples☆193Updated last year
- ARC gym: a data generation framework for the Abstraction & Reasoning Corpus☆23Updated 3 weeks ago
- ☆123Updated last year
- LLM sampling method for enforcing syntax adherence in generated output☆25Updated 2 years ago
- Language-annotated Abstraction and Reasoning Corpus☆93Updated 2 years ago
- ☆35Updated 2 years ago
- The history files when recording human interaction while solving ARC tasks☆115Updated this week
- Multi-Domain Expert Learning☆67Updated last year
- Chat Markup Language conversation library☆55Updated last year
- A dataset of alignment research and code to reproduce it☆77Updated 2 years ago
- [ICML 2023] "Outline, Then Details: Syntactically Guided Coarse-To-Fine Code Generation", Wenqing Zheng, S P Sharan, Ajay Kumar Jaiswal, …☆41Updated last year
- One stop shop for all things carp☆59Updated 3 years ago
- Evaluating majors LLMs on the Abstraction and Reasoning Corpus☆17Updated last year
- Factored Cognition Primer: How to write compositional language model programs☆49Updated 2 years ago
- ☆39Updated last year
- A new way to generate large quantities of high quality synthetic data (on par with GPT-4), with better controllability, at a fraction of …☆22Updated 11 months ago
- Tools for working with the Abstraction & Reasoning Corpus☆205Updated 3 weeks ago
- Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit☆63Updated 2 years ago
- Functional Benchmarks and the Reasoning Gap☆88Updated 11 months ago
- A programming language for formal/informal computation.☆41Updated last month
- An unofficial implementation of the Infini-gram model proposed by Liu et al. (2024)☆33Updated last year
- Zeus LLM Trainer is a rewrite of Stanford Alpaca aiming to be the trainer for all Large Language Models☆70Updated 2 years ago
- An MDL-based approach to the Abstraction and Reasoning Corpus (ARC) challenge☆20Updated last month
- Experiments for efforts to train a new and improved t5☆76Updated last year