Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
Found but Not Read: When Extracted Text Closes the Retrieval-Reading Gap in Document Vision-Language Models
Qingtao Xia, Siyao Cheng, Jiahua Bao +2
Retrieval-augmented document question answering assumes that once the right page is found, a vision-language model (VLM) can read it. We show that this assumption often fails, leav…
cs.CV2026
Pre-PEFT Probing: Weight Statistics and Perturbation Robustness for Layer Selection in VLM Vision Encoders
Qingtao Xia, Jiahua Bao, Siyao Cheng +1
We propose a pre-fine-tuning probing method for Parameter-Efficient Fine-Tuning (PEFT) layer selection, aiming to obtain more stable and higher gains with fewer trainable parameter…