3 papers
cs.CV2026
GenFirst: Generation Before Reconstruction for Stable End-to-End Latent Generative Modeling
Guangting Zheng, Yiyuan Zhang, Tao Yang +4
Latent generative models typically follow a two-stage pipeline, training a variational autoencoder for reconstruction and then a generative model on the frozen latent space. Since…
cs.CV2025
SimFlow: Simplified and End-to-End Training of Latent Normalizing Flows
Qinyu Zhao, Guangting Zheng, Tao Yang +4
Normalizing Flows (NFs) learn invertible mappings between the data and a Gaussian distribution. Prior works usually suffer from two limitations. First, they add random noise to tra…
cs.CV2025
FARMER: Flow AutoRegressive Transformer over Pixels
Guangting Zheng, Qinyu Zhao, Tao Yang +6
Directly modeling the explicit likelihood of the raw data distribution is key topic in the machine learning area, which achieves the scaling successes in Large Language Models by a…