HaiYang Li — accepted AI-conference papers

2025

Seemingly Redundant Modules Enhance Robust Odor Learning in Fruit Flies

HaiYang Li, Liao Yu, Qiang Yu, Yunliang Zang

NeurIPS 2025poster

Biological circuits have evolved to incorporate multiple modules that perform similar functions. In the fly olfactory circuit, both lateral inhibition (LI) and neuronal spike frequency adaptation (SFA) are thought to enhance pattern separation for odor learning. However, it remains unclear whether t…

Cited by 0 Source ↗Scholar ↗

2025

Segment Anything Model Meets Semi-supervised Medical Image Segmentation: A Novel Perspective

Haifeng Zhao, Haiyang Li, Leilei Ma, Dengdi Sun

NeurIPS 2025poster

The scarcity of annotated medical imaging data has driven significant progress in semi-supervised learning to alleviate reliance on expensive expert labeling. While foundational vision models such as the Segment Anything Model (SAM) exhibit robust generalization in generic segmentation tasks, their…

Cited by 0 Source ↗Scholar ↗