4 papers
SlimVLM: Sensitivity-aware Dynamic Structured Pruning with Adaptive Visual Token Selection for Efficient Vision-Language Models
Yaozhi Wen, Jialong Guo, Zhenliang Ni +2
While Vision-Language Models (VLMs) have demonstrated remarkable performance in processing and understanding both text and images, their large parameter sizes lead to significant c…
SVL: Empowering Spiking Neural Networks for Efficient 3D Open-World Understanding
Xuerui Qiu, Peixi Wu, Yaozhi Wen +5
Spiking Neural Networks (SNNs) provide an energy-efficient way to extract 3D spatio-temporal features. However, existing SNNs still exhibit a significant performance gap compared t…
EEG-FM-Compass: Progress, Benchmarking, and Future Directions for EEG Foundation Models
Dingkun Liu, Yuheng Chen, Zhu Chen +5
Electroencephalography (EEG) foundation models (FMs) have recently emerged as a promising paradigm for brain-computer interfaces, aiming to learn transferable neural representation…
RAICL: Retrieval-Augmented In-Context Learning for Vision-Language-Model Based EEG Seizure Detection
Siyang Li, Zhuoya Wang, Xiyan Gui +4
Electroencephalogram (EEG) decoding is a critical component of medical diagnostics, rehabilitation engineering, and brain-computer interfaces. However, contemporary decoding method…