3 papers
cs.CV2026
Latent Denoising Makes Good Tokenizers
Jiawei Yang, Tianhong Li, Lijie Fan +2
Despite their fundamental role, it remains unclear what properties could make tokenizers more effective for generative modeling. We observe that modern generative models share a co…
cs.CV2025
Unified Autoregressive Visual Generation and Understanding with Continuous Tokens
Lijie Fan, Luming Tang, Siyang Qin +11
We present UniFluid, a unified autoregressive framework for joint visual generation and understanding leveraging continuous visual tokens. Our unified autoregressive architecture p…
cs.LG2025
Fractal Generative Models
Tianhong Li, Qinyi Sun, Lijie Fan +1
Modularization is a cornerstone of computer science, abstracting complex functions into atomic building blocks. In this paper, we introduce a new level of modularization by abstrac…