David Wehr — accepted AI-conference papers

2025

GSPN-2: Efficient Parallel Sequence Modeling

Hongjun Wang, yitong jiang, Collin McCarthy, David Wehr, Hanrong Ye, Xinhao Li +9

NeurIPS 2025poster

Efficient vision transformer remains a bottleneck for high-resolution images and long-video related real-world applications. Generalized Spatial Propagation Network (GSPN) \cite{wang2025parallel} addresses this by replacing quadratic self-attention with a line-scan propagation scheme, bringing the c…

Cited by 0 Source ↗Scholar ↗

2020

MVLidarNet: Real-Time Multi-Class Scene Understanding for Autonomous Driving Using Multiple Views

Ke Chen, Ryan Oldja, Nikolai Smolyanskiy, Stan Birchfield, Alexander Popov, David Wehr +2

IROS 2020poster

Autonomous driving requires the inference of actionable information such as detecting and classifying objects, and determining the drivable space. To this end, we present Multi-View LidarNet (MVLidarNet), a two-stage deep neural network for multi-class object detection and drivable space segmentatio…

Cited by 39 Source ↗Scholar ↗