4 papers
IFNSO: Iteration-Free Newton-Schulz Orthogonalization
Chen Hu, Qianxi Zhao, Xiaochen Yuan +4
The Newton-Schulz (NS) iteration has become a key technique for orthogonalization in optimizers such as Muon and for optimization on the Stiefel manifold. Despite its effectiveness…
EagleVision: A Dual-Stage Framework with BEV-grounding-based Chain-of-Thought for Spatial Intelligence
Jiaxu Wan, Xu Wang, Mengwei Xie +6
Video-based spatial reasoning -- such as estimating distances, judging directions, or understanding layouts from multiple views -- requires selecting informative frames and, when n…
SPT: Sparse Proxy Attention for Dual-stream Point Transformer
Jiaxu Wan, Hong Zhang, Ziqi He +4
Point transformers have demonstrated remarkable progress in 3D understanding through expanded receptive fields (RF), but further expanding the RF leads to dilution in group attenti…
Unlocking Attributes' Contribution to Successful Camouflage: A Combined Textual and VisualAnalysis Strategy
Hong Zhang, Yixuan Lyu, Qian Yu +4
In the domain of Camouflaged Object Segmentation (COS), despite continuous improvements in segmentation performance, the underlying mechanisms of effective camouflage remain poorly…