6 papers
MIMFlow: Integrating Masked Image Modeling with Normalizing Flows for End-to-End Image Generation
Yang Chen, Xiaowei Xu, Shuai Wang +4
Normalizing Flows (NFs) are powerful generative models capable of exact density estimation and sampling. However, their strict invertibility often forces the model to exhaust its c…
Flowing Backwards: Improving Normalizing Flows via Reverse Representation Alignment
Yang Chen, Xiaowei Xu, Shuai Wang +5
Normalizing Flows (NFs) are a class of generative models distinguished by a mathematically invertible architecture, where the forward pass transforms data into a latent space for d…
PixNerd: Pixel Neural Field Diffusion
Shuai Wang, Ziteng Gao, Chenhui Zhu +2
The current success of diffusion transformers heavily depends on the compressed latent space shaped by the pre-trained variational autoencoder(VAE). However, this two-stage trainin…
Differentiable Solver Search for Fast Diffusion Sampling
Shuai Wang, Zexian Li, Qipeng zhang +5
Diffusion models have demonstrated remarkable generation quality but at the cost of numerous function evaluations. Recently, advanced ODE-based solvers have been developed to mitig…
DMM: Building a Versatile Image Generation Model via Distillation-Based Model Merging
Tianhui Song, Weixin Feng, Shuai Wang +4
The success of text-to-image (T2I) generation models has spurred a proliferation of numerous model checkpoints fine-tuned from the same base model on various specialized datasets.…
FlowDCN: Exploring DCN-like Architectures for Fast Image Generation with Arbitrary Resolution
Shuai Wang, Zexian Li, Tianhui Song +4
Arbitrary-resolution image generation still remains a challenging task in AIGC, as it requires handling varying resolutions and aspect ratios while maintaining high visual quality.…