2026
Bi-VLM: Binary Post-Training Quantization for Vision-Language Models
AAAI 2026technical
We address the critical gap between the computational demands of vision-language models and the possible ultra-low-bit weight precision (bitwidth
2 accepted papers
We address the critical gap between the computational demands of vision-language models and the possible ultra-low-bit weight precision (bitwidth
Text-Based Person Retrieval (TBPR) aims to accurately retrieve target individuals from large-scale image databases using only textual descriptions. Existing methods typically assume a ground-truth correspondence between text and images (i.e., strongly correlated). However, in real-world scenarios, t