Paper 'OmniSAM: Omnidirectional Segment Anything Model for UDA in Panoramic Semantic Segmentation' accepted by ICCV 2025 and selected as Highlight
Paper 'Benchmarking Multi-modal Semantic Segmentation under Sensor Failures: Missing and Noisy Modality Robustness' won Best Paper Award at CVPR Workshop (TMM-OpenWorld) 2025 (Top 1) and was selected as Oral Presentation (Top 6)
Paper 'UMSSS: A Visual Scene Semantic Segmentation Dataset for Underground Mines' accepted by ICASSP 2025
Paper 'An Efficient Large Kernel Convolution Network Designed for Neural Processing Unit' published in Engineering Applications of Artificial Intelligence
Preprint 'MemorySAM: Memorize Modalities and Semantics with Segment Anything Model 2 for Multi-modal Semantic Segmentation' posted on ArXiv in March 2025
Outstanding Bachelor’s Thesis in Beijing, China (2024)