An open API service providing repository metadata for many open source software ecosystems.

Topic: "compositional-generalization"

microsoft/ContextualSP

Multiple paper open-source codes of the Microsoft Research Asia DKI group

Language: Python - Size: 71 MB - Last synced at: 5 days ago - Pushed at: over 1 year ago - Stars: 379 - Forks: 61

Adamdad/Awesome-ComposableAI

A curated list of Composable AI methods: Building AI system by composing modules.

Size: 25 MB - Last synced at: 12 days ago - Pushed at: over 1 year ago - Stars: 193 - Forks: 5

FranxYao/Distributional-Generalization-in-Natural-Language-Processing

Distributional Generalization in NLP. A roadmap.

Language: Jupyter Notebook - Size: 5.94 MB - Last synced at: 19 days ago - Pushed at: over 2 years ago - Stars: 88 - Forks: 3

frankaging/Reason-SCAN

ReaSCAN is a synthetic navigation task that requires models to reason about surroundings over syntactically difficult languages. (NeurIPS '21)

Language: Python - Size: 4.12 MB - Last synced at: 20 days ago - Pushed at: over 3 years ago - Stars: 20 - Forks: 3

wqshmzh/CANet-CZSL

Official pytorch implementation of CVPR2023 paper "Learning Conditional Attributes for Compositional Zero-Shot Learning"

Language: Python - Size: 21.9 MB - Last synced at: 10 months ago - Pushed at: 10 months ago - Stars: 12 - Forks: 3

frankaging/Interchange-Intervention-Training

The codebase for Inducing Causal Structure for Interpretable Neural Networks

Language: Shell - Size: 17.6 KB - Last synced at: 20 days ago - Pushed at: over 3 years ago - Stars: 10 - Forks: 0

frankaging/ReCOGS

ReCOGS: How Incidental Details of a Logical Form Overshadow an Evaluation of Semantic Interpretation

Language: Jupyter Notebook - Size: 83.5 MB - Last synced at: 20 days ago - Pushed at: almost 2 years ago - Stars: 9 - Forks: 2

liqing-ustc/HINT

Official implementation of ICLR 2023 paper "A Minimalist Dataset for Systematic Generalization of Perception, Syntax, and Semantics"

Language: Jupyter Notebook - Size: 351 MB - Last synced at: about 1 year ago - Pushed at: almost 2 years ago - Stars: 5 - Forks: 0

frankaging/BabyARC

Baby Abstract Reasoning Corpus (BabyARC) dataset engine, for generating grid-world-based abstract reasoning tasks on a large scale.

Language: Python - Size: 2.85 MB - Last synced at: 25 days ago - Pushed at: over 3 years ago - Stars: 5 - Forks: 1

itayle/diverse-demonstrations

Diverse Demonstrations Improve In-context Compositional Generalization

Language: Python - Size: 22.4 MB - Last synced at: almost 2 years ago - Pushed at: almost 2 years ago - Stars: 3 - Forks: 0

Casparvolquardsen/Compositional-Generalization-in-Multimodal-Language-Learning

This repository shares the most important sources used for the reasearch paper "More Diverse Training, Better Compositionality! Evidence from Multimodal Language Learning" by Caspar Volquardsen, Jae Hee Lee, Cornelius Weber, and Stefan Wermter.

Language: Python - Size: 3.6 MB - Last synced at: over 1 year ago - Pushed at: about 2 years ago - Stars: 3 - Forks: 1

mmrl/lost-in-latent-space

Code from the article: "Lost in Latent Space: Examining Failures of Disentangled Models at Combinatorial Generalisaton" (NeurIPS, 2022)

Language: Python - Size: 87.9 KB - Last synced at: almost 2 years ago - Pushed at: over 2 years ago - Stars: 3 - Forks: 0

avi-otterai/compositional-generalization-lit-review

Living Survey for papers on Compositional Generalization in NLP

Language: Vue - Size: 1.73 MB - Last synced at: 4 days ago - Pushed at: 4 days ago - Stars: 2 - Forks: 0

Zhaoyi-Li21/compmctg_protocols

[ACL 2024] "Benchmarking and Improving Compositional Generalization of Multi-aspect Controllable Text Generation"

Language: Python - Size: 2.22 MB - Last synced at: 6 months ago - Pushed at: 6 months ago - Stars: 2 - Forks: 0

rahul13ramesh/compositional_capabilities

Compositional Capabilities of Autoregressive Transformers: A Study on Synthetic, Interpretable Tasks

Language: Python - Size: 24.4 KB - Last synced at: 10 months ago - Pushed at: 10 months ago - Stars: 2 - Forks: 0

frankaging/ReaSCAN-Causal

Causal Abstraction of Neural Models Trained to Solve ReaSCAN

Language: Python - Size: 49.6 MB - Last synced at: about 2 months ago - Pushed at: over 3 years ago - Stars: 1 - Forks: 0

miltonllera/ocdm

Object-Centric Disentangled Mechanisms

Language: Python - Size: 174 KB - Last synced at: about 1 year ago - Pushed at: about 1 year ago - Stars: 0 - Forks: 0

PoppyCollis/METATOOL_UoS

Minimal model of tool discovery and tool innovation using active inference

Language: Jupyter Notebook - Size: 7.59 MB - Last synced at: over 1 year ago - Pushed at: over 1 year ago - Stars: 0 - Forks: 2