mlsanityData to 7 Oct 2026

Conditional Set Generation with Transformers

arXiv 2006.16841 ↗First posted 26 Jun 2020cs.CV cs.LGcited by 32

Not on the map. Why?

Abstract (arXiv)

A set is an unordered collection of unique elements--and yet many machine learning models that generate sets impose an implicit or explicit ordering. Since model performance can depend on the choice of order, any particular ordering can lead to sub-optimal results. An alternative solution is to use a permutation-equivariant set generator, which does not specify an order-ing. An example of such a generator is the DeepSet Prediction Network (DSPN). We introduce the Transformer Set Prediction Network (TSPN), a flexible permutation-equivariant model for set prediction based on the transformer, that builds upon and outperforms DSPN in the quality of predicted set elements and in the accuracy of their predicted sizes. We test our model on MNIST-as-point-clouds (SET-MNIST) for point-cloud generation and on CLEVR for object detection.

Key facts. Cited by 32 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 7; 2023: 10; 2024: 1; 2025: 4; 2026: 1.

32 papers.

Sort:

By area:

  1. 2022Equivariant Diffusion for Molecule Generation in 3Dcited by 666
  2. 2021ATISS: Autoregressive Transformers for Indoor Scene Synthesiscited by 195
  3. 2021Decomposing 3D Scenes into Objects via Unsupervised Volume Segmentationcited by 88
  4. 2021SetVAE: Learning Hierarchical Composition for Generative Modeling of Set-Structured Datacited by 78
  5. 2022Complex-Valued Autoencoders for Object Discoverycited by 40
  6. 2021Top-N: Equivariant set and graph generation without exchangeabilitycited by 36
  7. 2023CaloClouds: Fast Geometry-Independent Highly-Granular Calorimeter Simulationcited by 33
  8. 2023Rotating Features for Object Discoverycited by 29
  9. 2021A Consciousness-Inspired Planning Agent for Model-Based Reinforcement Learningcited by 27
  10. 2023EPiC-GAN: Equivariant Point Cloud Generation for Particle Jetscited by 23
  11. 2021Multiset-Equivariant Set Prediction with Approximate Implicit Differentiationcited by 17
  12. 2023Prefix-Tree Decoding for Predicting Mass Spectra from Moleculescited by 16
20 more
  1. 2021multiPRover: Generating Multiple Proofs for Improved Interpretability in Rule Reasoningcited by 15
  2. 2023Object-Centric Learning with Slot Mixture Modulecited by 11
  3. 2022Learning Neural Set Functions Under the Optimal Subset Oraclecited by 10
  4. 2022Conditional set generation using Seq2seq modelscited by 7
  5. 2022Robust and Controllable Object-Centric Learning through Energy-based Modelscited by 7
  6. 2023Let There Be Order: Rethinking Ordering in Autoregressive Graph Generationcited by 7
  7. 2021Set-to-Sequence Methods in Machine Learning: a Reviewcited by 6
  8. 2025Audio synthesizer inversion in symmetric parameter spaces with approximately equivariant flow matchingcited by 6
  9. 2024Binding Dynamics in Rotating Featurescited by 5
  10. 2021Set Representation Learning with Generalized Sliced-Wasserstein Embeddingscited by 4
  11. 2023Permutation-Invariant Set Autoencoders with Fixed-Size Embeddings for Multi-Agent Learningcited by 4
  12. 2023AudioSlots: A slot-centric generative model for audio separationcited by 4
  13. 2025Advances in Set Function Learning: A Survey of Techniques and Applicationscited by 3
  14. 2022Search for Concepts: Discovering Visual Concepts Using Direct Optimizationcited by 2
  15. 2022Sequence-to-Set Generative Modelscited by 1
  16. 2023Image To Tree with Recursive Promptingcited by 1
  17. 2023Outfit Completion via Conditional Set Transformationcited by 0
  18. 2025Tokenize Image as a Setcited by 0
  19. 2025Compressive Meta-Learningcited by 0
  20. 2026GLASS: Global Latent Aggregation with Slot-based Set Decoding for Scalable All-Atom Crystal Generationcited by 0