10 papers
DiffusionBench: On Holistic Evaluation of Diffusion Transformers
Xingjian Leng, Jaskirat Singh, Zhanhao Liang +5
Diffusion transformer (DiT) research on image generation has converged to a single evaluation setup: class-conditional generation on ImageNet. While methods improve the FID and rel…
Improved Baselines with Representation Autoencoders
Jaskirat Singh, Boyang Zheng, Zongze Wu +3
Representation Autoencoders (RAE) replace traditional VAE with pretrained vision encoders. In this paper, we systematically investigate several design choices and find three insigh…
What matters for Representation Alignment: Global Information or Spatial Structure?
Jaskirat Singh, Xingjian Leng, Zongze Wu +4
Representation alignment (REPA) guides generative training by distilling representations from a strong, pretrained vision encoder to intermediate diffusion features. We investigate…
REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformers
Xingjian Leng, Jaskirat Singh, Yunzhong Hou +3
In this paper we tackle a fundamental question: "Can we train latent diffusion models together with the variational auto-encoder (VAE) tokenizer in an end-to-end manner?" Tradition…
Vec2Face+ for Face Dataset Generation
Haiyu Wu, Jaskirat Singh, Sicong Tian +2
When synthesizing identities as face recognition training data, it is generally believed that large inter-class separability and intra-class attribute variation are essential for s…
DiSA: Diffusion Step Annealing in Autoregressive Image Generation
Qinyu Zhao, Jaskirat Singh, Ming Xu +3
An increasing number of autoregressive models, such as MAR, FlowAR, xAR, and Harmon adopt diffusion sampling to improve the quality of image generation. However, this strategy lead…