Leye Wang

Unveiling the Secret of AdaLN-Zero in Diffusion Transformer

An Empirical Study of Multiple Masking in Masked Autoencoder

MoLE: Enhancing Human-centric Text-to-image Diffusion via Mixture of Low-rank Experts

Unlocking the Transferability of Tokens in Deep Models for Tabular Data

On Transferring Expert Knowledge from Tabular Data to Images

MoLE: Human-centric Text-to-image Diffusion with Mixture of Low-rank Experts

Conditional MAE: An Empirical Study of Multiple Masking in Masked Autoencoder