RobertCsordas / transformer_generalization
The official repository for our paper "The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers". We significantly improve the systematic generalization of transformer models on a variety of datasets using simple tricks and careful considerations.
☆66Updated last year
Related projects ⓘ
Alternatives and complementary repositories for transformer_generalization
- The official repository for our paper "The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalization".☆32Updated 3 years ago
- ☆38Updated 3 years ago
- [NeurIPS 2022] DataMUX: Data Multiplexing for Neural Networks☆59Updated 2 years ago
- ☆63Updated 2 years ago
- GPT, but made only out of MLPs☆87Updated 3 years ago
- This repository contains the code for running the character-level Sandwich Transformers from our ACL 2020 paper on Improving Transformer …☆55Updated 3 years ago
- ☆77Updated 3 months ago
- ☆42Updated 4 years ago
- Silly twitter torch implementations.☆46Updated 2 years ago
- ☆44Updated 3 years ago
- Skyformer: Remodel Self-Attention with Gaussian Kernel and Nystr\"om Method (NeurIPS 2021)☆59Updated 2 years ago
- Implementation of Gated State Spaces, from the paper "Long Range Language Modeling via Gated State Spaces", in Pytorch☆95Updated last year
- Usable implementation of Emerging Symbol Binding Network (ESBN), in Pytorch☆23Updated 3 years ago
- Code for "Discovering Non-monotonic Autoregressive Orderings with Variational Inference" (paper and code updated from ICLR 2021)☆11Updated 8 months ago
- An implementation of Transformer with Expire-Span, a circuit for learning which memories to retain☆33Updated 4 years ago
- ☆64Updated 4 years ago
- Official code repository of the paper Linear Transformers Are Secretly Fast Weight Programmers.☆100Updated 3 years ago
- ☆42Updated 3 years ago
- Code for the paper PermuteFormer☆42Updated 3 years ago
- ☆22Updated 3 years ago
- Official repository for the paper "Going Beyond Linear Transformers with Recurrent Fast Weight Programmers" (NeurIPS 2021)☆47Updated last year
- Code for the paper "Implicit Representations of Meaning in Neural Language Models"☆49Updated last year
- STABILIZING GRADIENTS FOR DEEP NEURAL NETWORKS VIA EFFICIENT SVD PARAMETERIZATION☆16Updated 6 years ago