Showing cs.CVShow all
3 papers · 1 filter
cs.CV2025
CodeV: Code with Images for Faithful Visual Reasoning via Tool-Aware Policy Optimization
Xinhai Hou, Shaoyuan Xu, Manan Biyani +4
Agentic vision-language models are increasingly trained to "think with images" by calling image operations. However, we show that high final-answer accuracy often hides unfaithful…
cs.CV2025
QID: Efficient Query-Informed ViTs in Data-Scarce Regimes for OCR-free Visual Document Understanding
Binh M. Le, Shaoyuan Xu, Jinmiao Fu +6
In Visual Document Understanding (VDU) tasks, fine-tuning a pre-trained Vision-Language Model (VLM) with new datasets often falls short in optimizing the vision encoder to identify…
cs.CV2023
Hierarchical Conditional Semi-Paired Image-to-Image Translation For Multi-Task Image Defect Correction On Shopping Websites
Moyan Li, Jinmiao Fu, Shaoyuan Xu +3
On shopping websites, product images of low quality negatively affect customer experience. Although there are plenty of work in detecting images with different defects, few efforts…