activity
20242026
collaborators

10 papers

cs.CV2026

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…

cs.CV2026

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…

cs.CV2025

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…

cs.CV2025

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…

cs.CV2025

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…

cs.CV2025

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…