A Neural Compositional Paradigm for Image Captioning
-
Updated
Apr 3, 2019 - Lua
A Neural Compositional Paradigm for Image Captioning
Code and results for experiments of CNNs (fairseq, Gehring et al., ICML, 2017) on SCAN dataset (Lake & Baroni, ICML, 2018)
Source code and supplementary material for DIRAC: Diffusion-Based Representation Learning for Modality-Agnostic Compositionality
Code for the CCE algorithm proposed in "Towards Compositionality in Concept Learning" at ICML 2024.
Code for Recursive Neural Programs: A differentiable framework for learning compositional part-whole hierarchies and image grammars
Maurer-Cartan-Lie frame connections ∇ Grassmann.jl TensorField derivations
[CVPR 2024] The official implementation of paper "synthesize, diagnose, and optimize: towards fine-grained vision-language understanding"
Implementing a transformer model for the SCAN compositionality tasks.
Official implementation and dataset for the NAACL 2024 paper "ComCLIP: Training-Free Compositional Image and Text Matching"
Living Survey for papers on Compositional Generalization in NLP
Tool to measure tree-structuredness of the internal algorithm learnt by a transformer
A PyTorch implementation of ideal word computation.
This repository contains RMarkdown with code to analyse sound similarity in novel vocalizations..
SVIB: Systematic Visual Imagination Benchmark
Implementation of the "Learn No to Say Yes Better" paper.
Codebase for analysing compositional generalisation in NMT models, which allows you to run systematicity, productivity, substitutivity and idiom processing analyses.
[ICCV 2023] Unsupervised Compositional Concepts Discovery with Text-to-Image Generative Models
Code repository for Capacity, Bandwidth, and Compositionality in Emergent Language Learning (AAMAS 2020)
Code for ICLR 2024 Paper: CompA: Addressing the Gap in Compositional Reasoning in Audio-Language Models
Add a description, image, and links to the compositionality topic page so that developers can more easily learn about it.
To associate your repository with the compositionality topic, visit your repo's landing page and select "manage topics."