logo
today local_bar
image tokenization

2 papers across 2 sessions

Poster Session 4

1 paper
Thursday, December 4, 2025 · 4:30 PM → 7:30 PM
Exhibit Hall C,D,E
Switchable Token-Specific Codebook Quantization For Face Image Compression
#4208 · Yongbo Wang, Haonan Wang, Guodong Mu, Ruixin Zhang, Jiaqi Chen, Jingyun Zhang, Jun Wang, Yuan Xie, zhizhong zhang, Shouhong Ding

Poster Session 6

1 paper
Friday, December 5, 2025 · 4:30 PM → 7:30 PM
Exhibit Hall C,D,E
CAT: Content-Adaptive Image Tokenization
#4605 · Junhong Shen, Kushal Tirumala, Michihiro Yasunaga, Ishan Misra, Luke Zettlemoyer, LILI YU, Chunting Zhou

We develop an adaptive image tokenizer that compresses images into variable-sized latent features based on its content complexity.