3 papers
cs.CV2026
Effective Prompt Pool Learning for Continual Category Discovery
Fernando Julio Cendra, Xinghui Li, Kai Han
This paper studies effective prompt pool learning for Continual Category Discovery (CCD), a challenging open-world setting where a model must discover novel categories from a conti…
cs.CV2026
Composable Visual Tokenizers with Generator-Free Diagnostics of Learnability
Bingchen Zhao, Qiushan Guo, Ye Wang +3
We introduce CompTok, a training framework for learning visual tokenizers whose tokens are enhanced for compositionality. CompTok uses a token-conditioned diffusion decoder. By emp…
cs.CV2025
Generalized Category Discovery under the Long-Tailed Distribution
Bingchen Zhao, Kai Han
This paper addresses the problem of Generalized Category Discovery (GCD) under a long-tailed distribution, which involves discovering novel categories in an unlabelled dataset usin…