3 papers
cs.CL2026
ERNIE 5.0 Technical Report
Haifeng Wang, Hua Wu, Tian Wu +432
In this report, we introduce ERNIE 5.0, a natively autoregressive foundation model desinged for unified multimodal understanding and generation across text, image, video, and audio…
cs.CV2025
Lightweight Backbone Networks Only Require Adaptive Lightweight Self-Attention Mechanisms
Fengyun Li, Chao Zheng, Yangyang Fang +4
Currently, lightweight hybrid backbone networks have partially alleviated the issue of computational saturation, but the imbalance in computational efficiencys between convolutiona…
cs.CV2025
MIA-Mind: A Multidimensional Interactive Attention Mechanism Based on MindSpore
Zhenkai Qin, Jiaquan Liang, Qiao Fang
Attention mechanisms have significantly advanced deep learning by enhancing feature representation through selective focus. However, existing approaches often independently model c…