Stop Mixing Things Up! BISCUIT Teaches Vision-Language Models to Learn New Concepts from Images on the Spot

Jiahua Bao, Siyao Cheng, Jiaxing Du, Yuhang Jia, Boyang Niu, Zeming Lang, Changjiang He, Hao Zhang, Jie LiuAAAI 2026 · DOI

BibTeX
@inproceedings{bao2026stop,
  author = {Jiahua Bao and Siyao Cheng and Jiaxing Du and Yuhang Jia and Boyang Niu and Zeming Lang and Changjiang He and Hao Zhang and Jie Liu},
  title = {{Stop Mixing Things Up! BISCUIT Teaches Vision-Language Models to Learn New Concepts from Images on the Spot}},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year = {2026},
  doi = {10.1609/aaai.v40i4.37226},
}

Loading related content...

Figure