PillarMamba: Learning Local-Global Context for Roadside Point Cloud via Hybrid State Space Model

no code implementations • 8 May 2025 • Zhang Zhang, Chao Sun, Chao Yue, Da Wen, Tianze Wang, Jianghao Leng

In this work, we introduce Mamba to pillar-based roadside point cloud perception and propose a framework based on Cross-stage State-space Group (CSG), called PillarMamba.

3D Object Detection Mamba

HeightFormer: Learning Height Prediction in Voxel Features for Roadside Vision Centric 3D Object Detection via Transformer

no code implementations • 13 Mar 2025 • Zhang Zhang, Chao Sun, Chao Yue, Da Wen, Yujie Chen, Tianze Wang, Jianghao Leng

BEV features and voxel features present the real distribution of objects in 3D world compared to the image features.

3D Object Detection Autonomous Vehicles +1

A Neural Symbolic Model for Space Physics

1 code implementation • 11 Mar 2025 • Jie Ying, Haowei Lin, Chao Yue, Yajie Chen, Chao Xiao, Quanqi Shi, Yitao Liang, Shing-Tung Yau, Yuan Zhou, Jianzhu Ma

In this study, we unveil a new AI model, termed PhyE2E, to discover physical formulas through symbolic regression.

Large Language Model model +1

FR: Folded Rationalization with a Unified Encoder

1 code implementation • 17 Sep 2022 • Wei Liu, Haozhao Wang, Jun Wang, Ruixuan Li, Chao Yue, Yuankai Zhang

Conventional works generally employ a two-phase model in which a generator selects the most important pieces, followed by a predictor that makes predictions based on the selected pieces.