2 papers
cs.CV2025
Emerging Properties in Unified Multimodal Pretraining
Chaorui Deng, Deyao Zhu, Kunchang Li +9
Unifying multimodal understanding and generation has shown impressive capabilities in cutting-edge proprietary systems. In this work, we introduce BAGEL, an open-source foundationa…
cs.CV2024
Causal Diffusion Transformers for Generative Modeling
Chaorui Deng, Deyao Zhu, Kunchang Li +2
We introduce Causal Diffusion as the autoregressive (AR) counterpart of Diffusion models. It is a next-token(s) forecasting framework that is friendly to both discrete and continuo…