On a proprietary tire-architecture dataset, diffusion models outperform VAEs and GANs overall; a masking-trained VAE beats MMVAE+ on component-conditioned generation, and MDM is best in-distribution while DDPM generalizes better out-of-distribution.
Towards high-fidelity cfd on the cloud for the automotive and motorsport sectors,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Deep Generative Methods and Tire Architecture Design
On a proprietary tire-architecture dataset, diffusion models outperform VAEs and GANs overall; a masking-trained VAE beats MMVAE+ on component-conditioned generation, and MDM is best in-distribution while DDPM generalizes better out-of-distribution.