mlsanityData to 7 Oct 2026

Visual Conceptual Blending with Large-scale Language and Vision Models

arXiv 2106.14127 ↗First posted 27 Jun 2021cs.CL cs.AI cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

We ask the question: to what extent can recent large-scale language and image generation models blend visual concepts? Given an arbitrary object, we identify a relevant object and generate a single-sentence description of the blend of the two using a language model. We then generate a visual depiction of the blend using a text-based image generation model. Quantitative and qualitative evaluations demonstrate the superiority of language models over classical methods for conceptual blending, and of recent large-scale image generation models over prior models for the visual depiction.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 16 of its 39 references that are in the map. First posted on arXiv 27 Jun 2021.

Builds on

16 of 39 references.

References · 16

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  5. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  6. 2018Deep contextualized word representationscited by 2,285
  7. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
  8. 2019Language Models as Knowledge Bases?cited by 1,922
  9. 2016ConceptNet 5.5: An Open Multilingual Graph of General Knowledgecited by 1,065
  10. 2019How Can We Know What Language Models Know?cited by 953
  11. 2016Generative Adversarial Text to Image Synthesiscited by 735
  12. 2019DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesiscited by 308
4 more
  1. 2020Rewriting a Deep Generative Modelcited by 105
  2. 2017Analogical Inference for Multi-Relational Embeddingscited by 69
  3. 2016Deep Convolutional Networks as Models of Generalization and Blending Within Visual Creativitycited by 1
  4. 2017A Pig, an Angel and a Cactus Walk Into a Blender: A Descriptive Approach to Visual Blendingcited by 1

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 1; 2024: 0; 2025: 1.

3 papers.

  1. 2023AI's Regimes of Representation: A Community-centered Study of Text-to-Image Models in South Asiacited by 54
  2. 20223DALL-E: Integrating Text-to-Image AI in 3D Design Workflowscited by 41
  3. 2025Blending Concepts with Text-to-Image Diffusion Modelscited by 0