Bi-VLM: Binary Post-Training Quantization for Vision-Language Models

Xijun Wang; Rayyan Abdalla; Junyun Huang; Chengyuan Zhang; Ruiqi Xian; Dinesh Manocha

AAAI 2026technical0 citations

Bi-VLM: Binary Post-Training Quantization for Vision-Language Models

Xijun Wang, Rayyan Abdalla, Junyun Huang, Chengyuan Zhang, Ruiqi Xian, Dinesh Manocha

Abstract

We address the critical gap between the computational demands of vision-language models and the possible ultra-low-bit weight precision (bitwidth

BibTeX

@inproceedings{aaai2026_bivlmbinarypostt,
  title = {Bi-VLM: Binary Post-Training Quantization for Vision-Language Models},
  author = {Xijun Wang and Rayyan Abdalla and Junyun Huang and Chengyuan Zhang and Ruiqi Xian and Dinesh Manocha},
  booktitle = {AAAI 2026},
  year = {2026}
}