4 papers
Efficient3D: A Unified Framework for Adaptive and Debiased Token Reduction in 3D MLLMs
Yuhui Lin, Siyue Yu, Yuxing Yang +2
Recent advances in Multimodal Large Language Models (MLLMs) have expanded reasoning capabilities into 3D domains, enabling fine-grained spatial understanding. However, the substant…
Hypergraph Mamba for Efficient Whole Slide Image Understanding
Jiaxuan Lu, Yuhui Lin, Junyan Shi +4
Whole Slide Images (WSIs) in histopathology pose a significant challenge for extensive medical image analysis due to their ultra-high resolution, massive scale, and intricate spati…
MV-GMN: State Space Model for Multi-View Action Recognition
Yuhui Lin, Jiaxuan Lu, Yue Yong +1
Recent advancements in multi-view action recognition have largely relied on Transformer-based models. While effective and adaptable, these models often require substantial computat…
Event USKT : U-State Space Model in Knowledge Transfer for Event Cameras
Yuhui Lin, Jiahao Zhang, Siyuan Li +4
Event cameras, as an emerging imaging technology, offer distinct advantages over traditional RGB cameras, including reduced energy consumption and higher frame rates. However, the…