2 papers
cs.CV2026
GSA-YOLO: A High-Efficiency Framework via Structured Sparsity and Adaptive Knowledge Distillation for Real-Time X-ray Security Inspection
Jiahao Kong
X-ray security inspection requires accurate real-time detection of prohibited items, but existing models often struggle to balance the challenges of severe occlusion, complex clutt…
cs.CL2026
CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence
Dongsheng Ma, Jiayu Li, Zhengren Wang +8
Multimodal Large Language Models (MLLMs) have significantly advanced document understanding, yet current Doc-VQA evaluations score only the final answer and leave the supporting ev…