The official repository for our paper "The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalization".
☆34Jun 11, 2025Updated last year
Alternatives and similar repositories for ndr
Users that are interested in ndr are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Paper: Lexicon Learning for Few-Shot Neural Sequence Modeling☆17Jan 8, 2022Updated 4 years ago
- Official Repository for "Modeling Hierarchical Structures with Continuous Recursive Neural Networks" (ICML 2021)☆12Aug 18, 2021Updated 5 years ago
- Code publication to the paper "Normalized Attention Without Probability Cage"☆17Aug 24, 2026Updated 2 months ago
- sigma-MoE layer☆21Jan 5, 2024Updated 2 years ago
- ☆16Dec 9, 2023Updated 2 years ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Fine-Tuning Pre-trained Transformers into Decaying Fast Weights☆20Oct 9, 2022Updated 4 years ago
- Paper: Learning to Recombine and Resample Data for Compositional Generalization☆11Oct 9, 2020Updated 6 years ago
- Code for the paper "Query-Key Normalization for Transformers"☆53Mar 6, 2021Updated 5 years ago
- Datasets for compositional learning☆11Nov 28, 2018Updated 7 years ago
- ☆15Mar 20, 2025Updated last year
- ☆11Jan 2, 2022Updated 4 years ago
- ☆11Jul 25, 2021Updated 5 years ago
- ☆29Nov 30, 2021Updated 4 years ago
- ☆29May 4, 2024Updated 2 years ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Measuring if attention is explanation with ROAR☆22Mar 3, 2023Updated 3 years ago
- [ECCV'24 Oral] Chameleon: A Data-Efficient Generalist for Dense Visual Prediction in the Wild☆14Mar 13, 2025Updated last year
- ☆40Jan 11, 2021Updated 5 years ago
- Maximal Mutual Information (MMI) Tagger☆26Jun 6, 2019Updated 7 years ago
- Deep Generative Models (Chainer)☆10Oct 12, 2017Updated 9 years ago
- [NeurIPS 2023] Make Your Pre-trained Model Reversible: From Parameter to Memory Efficient Fine-Tuning☆33Jun 2, 2023Updated 3 years ago
- ☆13Aug 19, 2024Updated 2 years ago
- Complexity vs. Accuracy: On Mechanistic Interpretability's Dependence on the Linear Representation Hypothesis☆14Oct 9, 2025Updated last year
- Reference implementation of "Softmax Attention with Constant Cost per Token" (Heinsen, 2024)☆25Jun 6, 2024Updated 2 years ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- The accompanying code for "Memory-efficient Transformers via Top-k Attention" (Ankit Gupta, Guy Dar, Shaya Goodman, David Ciprut, Jonatha…☆70Sep 19, 2021Updated 5 years ago
- Author implementation of the paper "Span-based Semantic Parsing for Compositional Generalization"☆17Aug 29, 2021Updated 5 years ago
- An Empirical Comparison of Unsupervised Constituency Parsing Methods☆14Aug 15, 2021Updated 5 years ago
- Variable-order CRFs with structure learning☆17Oct 16, 2026Updated 3 weeks ago
- Official repository of paper "RNNs Are Not Transformers (Yet): The Key Bottleneck on In-context Retrieval"☆27Apr 17, 2024Updated 2 years ago
- Silly twitter torch implementations.☆48Oct 14, 2022Updated 4 years ago
- Factor Graph Grammars in Python☆14Jan 17, 2026Updated 9 months ago
- ACL 2022: Revisiting the Compositional Generalization Abilities of Neural Sequence Models☆13Oct 23, 2024Updated 2 years ago
- Add note-taking to semantic scholar☆11Apr 10, 2023Updated 3 years ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Sequence-Level Mixed Sample Data Augmentation☆22Mar 7, 2021Updated 5 years ago
- Implementation of a Transformer that Ponders, using the scheme from the PonderNet paper☆85Oct 30, 2021Updated 5 years ago
- ☆31Mar 7, 2022Updated 4 years ago
- ☆16Aug 14, 2022Updated 4 years ago
- ☆36Oct 3, 2018Updated 8 years ago
- Mine conversations from novels in Project Gutenberg, to generate data for data-driven dialogue systems.☆15May 7, 2019Updated 7 years ago
- source code of COLING2020 "Second-Order Unsupervised Neural Dependency Parsing"☆16Oct 24, 2022Updated 4 years ago