6 papers
MathDoc: Benchmarking Structured Extraction and Active Refusal on Noisy Mathematics Exam Papers
Chenyue Zhou, Jiayi Tuo, Shitong Qin +7
The automated extraction of structured questions from paper-based mathematics exams is fundamental to intelligent education, yet remains challenging in real-world settings due to s…
Calibrating Biased Distribution in VFM-derived Latent Space via Cross-Domain Geometric Consistency
Yanbiao Ma, Wei Dai, Bowei Liu +5
Despite the fast progress of deep learning, one standing challenge is the gap of the observed training samples and the underlying true distribution. There are multiple reasons for…
Geometric Origins of Bias in Deep Neural Networks: A Human Visual System Perspective
Yanbiao Ma, Bowei Liu, Andi Zhang
Bias formation in deep neural networks (DNNs) remains a critical yet poorly understood challenge, influencing both fairness and reliability in artificial intelligence systems. Insp…
Compositional Attribute Imbalance in Vision Datasets
Jiayi Chen, Yanbiao Ma, Andi Zhang +3
Visual attribute imbalance is a common yet underexplored issue in image classification, significantly impacting model performance and generalization. In this work, we first define…
Geometric Knowledge-Guided Localized Global Distribution Alignment for Federated Learning
Yanbiao Ma, Wei Dai, Wenke Huang +1
Data heterogeneity in federated learning, characterized by a significant misalignment between local and global distributions, leads to divergent local optimization directions and h…
Pursuing Better Decision Boundaries for Long-Tailed Object Detection via Category Information Amount
Yanbiao Ma, Wei Dai, Jiayi Chen
In object detection, the instance count is typically used to define whether a dataset exhibits a long-tail distribution, implicitly assuming that models will underperform on catego…