June 5, 2024, 4:43 a.m. | Yicheng Xiao, Lin Song, Shaoli Huang, Jiangshan Wang, Siyu Song, Yixiao Ge, Xiu Li, Ying Shan

cs.LG updates on arXiv.org arxiv.org

arXiv:2406.02395v1 Announce Type: new
Abstract: The state space models, employing recursively propagated features, demonstrate strong representation capabilities comparable to Transformer models and superior efficiency. However, constrained by the inherent geometric constraints of sequences, it still falls short in modeling long-range dependencies. To address this issue, we propose the GrootVL network, which first dynamically generates a tree topology based on spatial relationships and input features. Then, feature propagation is performed based on this graph, thereby breaking the original sequence constraints to …

abstract arxiv capabilities constraints cs.cv cs.lg dependencies efficiency features however issue modeling representation space state state space model state space models topology transformer transformer models tree type you

Senior Data Engineer

@ Displate | Warsaw

Junior Data Analyst - ESG Data

@ Institutional Shareholder Services | Mumbai

Intern Data Driven Development in Sensor Fusion for Autonomous Driving (f/m/x)

@ BMW Group | Munich, DE

Senior MLOps Engineer, Machine Learning Platform

@ GetYourGuide | Berlin

Data Engineer, Analytics

@ Meta | Menlo Park, CA

Data Engineer

@ Meta | Menlo Park, CA