brendenlake / MLCLinks
Meta-Learning for Compositionality (MLC) for modeling human behavior
☆143Updated last year
Alternatives and similar repositories for MLC
Users that are interested in MLC are comparing it to the libraries listed below
Sorting:
- Applying Behaviorally-Informed Meta-Learning (BIML) to machine learning benchmarks☆51Updated last year
- ☆210Updated 2 years ago
- Emergent world representations: Exploring a sequence model trained on a synthetic task☆188Updated 2 years ago
- ☆180Updated 2 weeks ago
- Extracting spatial and temporal world models from LLMs☆255Updated last year
- ☆99Updated last year
- Code for "Learning to Model the World with Language." ICML 2024 Oral.☆390Updated last year
- ☆185Updated last year
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆129Updated 2 years ago
- Public repository for "The Surprising Effectiveness of Test-Time Training for Abstract Reasoning"☆328Updated 9 months ago
- Materials for ConceptARC paper☆100Updated 9 months ago
- Bootstrapping ARC☆143Updated 9 months ago
- Intrinsic Motivation from Artificial Intelligence Feedback☆131Updated last year
- Efficient World Models with Context-Aware Tokenization. ICML 2024☆107Updated 11 months ago
- Repository for the paper Stream of Search: Learning to Search in Language☆150Updated 6 months ago
- Implementation of Recurrent Memory Transformer, Neurips 2022 paper, in Pytorch☆413Updated 7 months ago
- ☆68Updated 2 years ago
- OMNI: Open-endedness via Models of human Notions of Interestingness☆55Updated 7 months ago
- A MAD laboratory to improve AI architecture designs 🧪☆127Updated 8 months ago
- SmartPlay is a benchmark for Large Language Models (LLMs). Uses a variety of games to test various important LLM capabilities as agents. …☆140Updated last year
- ☆30Updated 5 months ago
- Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)☆192Updated last year
- maze datasets for investigating OOD behavior of ML systems☆53Updated last week
- ☆127Updated last year
- ☆59Updated 10 months ago
- An AI benchmark for creative, human-like problem solving using Sudoku variants☆91Updated last month
- ☆52Updated last year
- Code for Contrastive Preference Learning (CPL)☆175Updated 9 months ago
- Code for NeurIPS'24 paper 'Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization'☆229Updated last month
- Brain-Inspired Modular Training (BIMT), a method for making neural networks more modular and interpretable.☆172Updated 2 years ago