azreasoners / recurrent_transformer
☆8Updated last year
Alternatives and similar repositories for recurrent_transformer:
Users that are interested in recurrent_transformer are comparing it to the libraries listed below
- Official code for paper: INT: An Inequality Benchmark for Evaluating Generalization in Theorem Proving☆39Updated 2 years ago
- ☆49Updated last year
- Efficient empirical NTKs in PyTorch☆18Updated 2 years ago
- This repository includes code to reproduce the tables in "Loss Landscapes are All You Need: Neural Network Generalization Can Be Explaine…☆36Updated 2 years ago
- ☆9Updated 2 years ago
- Experiments and code to generate the GINC small-scale in-context learning dataset from "An Explanation for In-context Learning as Implici…☆106Updated last year
- ☆12Updated last year
- unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"☆78Updated 2 years ago
- ☆31Updated 6 months ago
- ☆28Updated 2 months ago
- Code repository for "The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks"☆15Updated last year
- ☆92Updated 2 months ago
- Deep Learning & Information Bottleneck☆60Updated last year
- Code for papers Linear Algebra with Transformers (TMLR) and What is my Math Transformer Doing? (AI for Maths Workshop, Neurips 2022)☆68Updated 8 months ago
- A Scalable Approximate Method for Probabilistic Neurosymbolic Inference☆15Updated 3 months ago
- ☆62Updated 3 years ago
- ☆34Updated last year
- ☆33Updated last year
- Universal Neurons in GPT2 Language Models☆28Updated 11 months ago
- Sparse and discrete interpretability tool for neural networks☆61Updated last year
- Abstract Reasoning with Graph Abstractions (ARGA) implementation☆61Updated 10 months ago
- ☆67Updated last year
- Code for the paper "Pretraining task diversity and the emergence of non-Bayesian in-context learning for regression"☆21Updated last year
- Code for our paper "Generative Flow Networks for Discrete Probabilistic Modeling"☆82Updated 2 years ago
- Official repository for the paper "Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks"☆59Updated 3 years ago
- Code Release for "Broken Neural Scaling Laws" (BNSL) paper☆58Updated last year
- Code for the paper "Decomposing the Enigma: Subgoal-based Demonstration Learning for Formal Theorem Proving"☆19Updated last year
- ☆34Updated 4 months ago
- This repository holds the code for the NeurIPS 2022 paper, Semantic Probabilistic Layers☆27Updated last year
- The Energy Transformer block, in JAX☆57Updated last year