Multiple paper open-source codes of the Microsoft Research Asia DKI group
ReaSCAN is a synthetic navigation task that requires models to reason about surroundings over syntactically difficult languages. (NeurIPS '21)
Official pytorch implementation of CVPR2023 paper "Learning Conditional Attributes for Compositional Zero-Shot Learning"
Diverse Demonstrations Improve In-context Compositional Generalization
[ACL'2023 Oral] "Learning to Substitute Span towards Improving Compositional Generalization"
Compositional Capabilities of Autoregressive Transformers: A Study on Synthetic, Interpretable Tasks
Code from the article: "Lost in Latent Space: Examining Failures of Disentangled Models at Combinatorial Generalisaton" (NeurIPS, 2022)
Baby Abstract Reasoning Corpus (BabyARC) dataset engine, for generating grid-world-based abstract reasoning tasks on a large scale.
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.
[ACL 2024] "Benchmarking and Improving Compositional Generalization of Multi-aspect Controllable Text Generation"
Causal Abstraction of Neural Models Trained to Solve ReaSCAN
Object-Centric Disentangled Mechanisms
Add a description, image, and links to the compositional-generalization topic page so that developers can more easily learn about it.
To associate your repository with the compositional-generalization topic, visit your repo's landing page and select "manage topics."