45 citations · 72 across the 39 of their papers we have counts for
7 papers · 1 filter
Anchor and Adapt: Asymmetric Prompt Adaptation for Few-Shot Industrial Anomaly Detection
Mengyang Zhao, Teng Fu, Haiyang Yu +3
In few-shot industrial anomaly detection, the few normal target images provide no direct defect supervision, making anomaly prompts difficult to learn from these samples alone. Som…
IterCAD: Iterative Program Repair for CAD Code Generation from Orthographic Views
Yuchuan Wu, Ke Niu, Haiyang Yu +3
Generating executable parametric CAD code from dimension-annotated orthographic drawings is a challenging task requiring geometric understanding, procedural reasoning, and precise…
SAGE: From Direct Answering to Evidence-Grounded Inference for Chinese Ancient Document Understanding
Yuchuan Wu, Xuan Luo, Yinglian Zhu +3
Chinese ancient document understanding demands complex visual, linguistic, and historical reasoning. Current Large Vision-Language Models (LVLMs) typically rely on an opaque, singl…
ResPrune: Text-Conditioned Subspace Reconstruction for Visual Token Pruning in Large Vision-Language Models
Xu Li, Yi Zheng, Yuxuan Liang +5
Large Vision-Language Models (LVLMs) rely on dense visual tokens to capture fine-grained visual information, but processing all these tokens incurs substantial computational and me…
DynamicVGGT: Learning Dynamic Point Maps for 4D Scene Reconstruction in Autonomous Driving
Zhuolin He, Jing Li, Guanghao Li +9
Dynamic scene reconstruction in autonomous driving remains a fundamental challenge due to significant temporal variations, moving objects, and complex scene dynamics. Existing feed…
AMR-CCR: Anchored Modular Retrieval for Continual Chinese Character Recognition
Yuchuan Wu, Yinglian Zhu, Haiyang Yu +3
Ancient Chinese character recognition is a core capability for cultural heritage digitization, yet real-world workflows are inherently non-stationary: newly excavated materials are…
DocCogito: Aligning Layout Cognition and Step-Level Grounded Reasoning for Document Understanding
Yuchuan Wu, Minghan Zhuo, Teng Fu +3
Document understanding with multimodal large language models (MLLMs) requires not only accurate answers but also explicit, evidence-grounded reasoning, especially in high-stakes sc…