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

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

Distributional Generalization in NLP. A roadmap.

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

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

Diverse Demonstrations Improve In-context Compositional Generalization

The codebase for Inducing Causal Structure for Interpretable Neural Networks

Benchmarks for Compose by Focus: Scene Graph-based Atomic Skills

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

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.

[ACL 2023] "Learning to Substitute Span towards Improving Compositional Generalization"

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

Iterative Compositional Data Generation for Robot Control

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.

Object-Centric Disentangled Mechanisms

Reproducible emergent AI communication experiments at the information-theoretic limit

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

Living Survey for papers on Compositional Generalization in NLP