Learning generative models with invariance to symmetries

Turnitin 降AI改写 早检测系统 早降重系统 Turnitin-UK版 万方检测-期刊版 维普编辑部版 Grammarly检测 Paperpass检测 checkpass检测 PaperYY检测
[Free GPT-4]
[DeepSeek]
[PDF] arxiv.org

Neural approximate mirror maps for constrained diffusion models

BT Feng, R Baptista, KL Bouman - arxiv preprint arxiv:2406.12816, 2024 - arxiv.org
Diffusion models excel at creating visually-convincing images, but they often struggle to
meet subtle constraints inherent in the training data. Such constraints could be physics …
Zapisz Cytuj Cytowane przez 1 Powiązane artykuły Wszystkie wersje 2 Wersja HTML
[Free GPT-4]
[DeepSeek]
[PDF] arxiv.org

A generative model of symmetry transformations

JU Allingham, BK Mlodozeniec, S Padhy… - arxiv preprint arxiv …, 2024 - arxiv.org
Correctly capturing the symmetry transformations of data can lead to efficient models with
strong generalization capabilities, though methods incorporating symmetries often require …
Zapisz Cytuj Cytowane przez 2 Powiązane artykuły Wszystkie wersje 2 Wersja HTML