Author
Chongjian Ge
Papers that credit Chongjian Ge in their source bylines. Matching names may refer to different researchers.
2 results
A two-stage method separates visual learning from rendering
A two-stage image method scored higher than tested latent-diffusion pretraining at matched image exposure.
A test compares language-model research across nine goals
Auto-Research Arena compares language-model research systems across nine efficiency goals; no tested system dominates them all.
