RobertCsordas / transformer_generalizationView external linksLinks
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.
☆67Dec 16, 2022Updated 3 years ago
Alternatives and similar repositories for transformer_generalization
Users that are interested in transformer_generalization are comparing it to the libraries listed below
Sorting:
- 📄 Evidence Retrieval and Claim Verification for the FEVER shared task using Transformer Networks☆12Feb 21, 2020Updated 5 years ago
- ☆44Aug 2, 2021Updated 4 years ago
- Code for gradient rollback, which explains predictions of neural matrix factorization models, as for example used for knowledge base comp…☆21Mar 16, 2021Updated 4 years ago
- Unofficially Implements https://arxiv.org/abs/2112.05682 to get Linear Memory Cost on Attention for PyTorch☆12Jan 16, 2022Updated 4 years ago
- Code for reproducing the results from the paper Avoiding Side Effects in Complex Environments☆12Jun 3, 2021Updated 4 years ago
- ☆45Oct 11, 2021Updated 4 years ago
- The official repository for our paper "Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks". We…☆46Oct 3, 2023Updated 2 years ago
- Scale your ML workers asynchronously across processes and machines☆13Apr 1, 2025Updated 10 months ago
- Uncertainty-Guided Pseudo-Labelling with Model Averaging☆11Sep 24, 2024Updated last year
- Generate multiple choice fill-in-the-blank questions from any article.☆13Dec 8, 2022Updated 3 years ago
- Tensorflow implementation of MuZero algorithm☆11Aug 23, 2022Updated 3 years ago
- Code and results accompanying our paper titled Leveraging Unlabeled Data to Predict Out-of-Distribution Performance at ICLR 2022☆10Dec 8, 2022Updated 3 years ago
- 🖼️📊☆11Jun 9, 2020Updated 5 years ago
- Implementation of Token Shift GPT - An autoregressive model that solely relies on shifting the sequence space for mixing☆49Jan 27, 2022Updated 4 years ago
- XtremeDistil framework for distilling/compressing massive multilingual neural network models to tiny and efficient models for AI at scale☆157Dec 20, 2023Updated 2 years ago
- Official codebase for Pretrained Transformers as Universal Computation Engines.☆246Jan 14, 2022Updated 4 years ago
- Universal Python binding for the LMDB 'Lightning' Database☆13Nov 7, 2017Updated 8 years ago
- The Return of Lexical Dependencies: Neural Lexicalized PCFGs (TACL)☆33Sep 22, 2025Updated 4 months ago
- ☆10Jul 27, 2018Updated 7 years ago
- ☆11Jun 2, 2021Updated 4 years ago
- The corresponding code from our paper "Social Commonsense Reasoning with Multi-Head Knowledge Attention (EMNLP 2020)". Do not hesitate to…☆11Jun 12, 2022Updated 3 years ago
- awesome unsupervised learning paper list☆12Jan 4, 2018Updated 8 years ago
- A neural text style transfer model☆12Jun 23, 2019Updated 6 years ago
- COMIC: This is the code repo of our TMM2019 work titled "COMIC: Towards a Compact Image Captioning Model with Attention".☆15Jun 22, 2021Updated 4 years ago
- Codebase implementing LMs for learning the Dyck-(k,m) bounded hierarchical language☆16Oct 11, 2020Updated 5 years ago
- Debiasing Methods in Natural Language Understanding Make Bias More Accessible: Code and Data☆14Apr 24, 2022Updated 3 years ago
- code for the table-based open domain question answering project, with paper title: "Reasoning over Hybrid Chain for Table-and-Text Open D…☆12Sep 16, 2022Updated 3 years ago
- Training vision models with full-batch gradient descent and regularization☆39Feb 14, 2023Updated 3 years ago
- The dataset and code for ACL 2022 paper "SciNLI: A Corpus for Natural Language Inference on Scientific Text" are released here.☆28Oct 17, 2023Updated 2 years ago
- ☆32Dec 10, 2020Updated 5 years ago
- Code Repo for "Differentiable Open-Ended Commonsense Reasoning" (NAACL 2021)☆32Jun 30, 2023Updated 2 years ago
- ☆18Jun 10, 2022Updated 3 years ago
- ICLR 2022 paper☆16May 6, 2022Updated 3 years ago
- An example docker container for runtime evaluation for the WIDER 2019 challenge track: face detection accuracy and runtime.☆17Aug 7, 2019Updated 6 years ago
- Implementation of Analyzing and Improving the Image Quality of StyleGAN (StyleGAN 2) in PyTorch☆15May 31, 2020Updated 5 years ago
- ☆16Mar 14, 2024Updated last year
- Paper: Lexicon Learning for Few-Shot Neural Sequence Modeling☆16Jan 8, 2022Updated 4 years ago
- ☆34Aug 30, 2021Updated 4 years ago
- Understanding Training Dynamics of Deep ReLU Networks☆306Oct 19, 2025Updated 3 months ago