Si-Yuan Lu — accepted AI-conference papers

2026

Confusion-Aware Spectral Regularizer for Long-Tailed Recognition

Ziquan Zhu, Gaojie Jin, Hanruo Zhu, Si-Yuan Lu, Yunxiao Zhang, Zeyu Fu +8

CVPR 2026

Long-tailed image classification remains a long-standing challenge, as real-world data typically follow highly imbalanced distributions where a few head classes dominate and many tail classes contain only limited samples. This imbalance biases feature learning toward head categories and leads to sig

Cited by 0 Source ↗code ↗Scholar ↗

2026

Dual-Kernel Adapter: Expanding Spatial Horizons for Data-Constrained Medical Image Analysis

Ziquan Zhu, Hanruo Zhu, Si-Yuan Lu, Xiang Li, Yanda Meng, Yunxiao Zhang +6

ICLR 2026poster

Adapters have become a widely adopted strategy for efficient fine-tuning of foundation models, particularly in resource-constrained settings. However, their performance under extreme data scarcity—common in medical imaging due to high annotation costs, privacy regulations, and fragmented datasets—re…

Cited by 0 Source ↗Scholar ↗