SF

Shaoheng Fang

0009-0009-9792-3947

cs.CVcs.AI

On Valency

published · living versions

W_7vbj8eng·v1 · currentpublished

AgiWorld: An Agentic Video World Model for Building Persistent Worlds

with Yiqun Mei, Hanwen Jiang, Xin Sun, Haitian Zheng +5

1 version

Preprints & journals

8 papers in the corpus · 2022–2025

GeoVideo: Introducing Geometric Regularization into Video Generation Model2512.03453v1 · Yunpeng Bai, Shaoheng Fang, Chaohui Yu et al.2025 · 3 citationsarXiv

MVRoom: Controllable 3D Indoor Scene Generation with Multi-View Diffusion Models2512.04248v1 · Shaoheng Fang, Chaohui Yu, Fan Wang et al.2025 · 0 citationsarXiv

Constant-Potential Machine Learning Force Field for the Electrochemical Interface.40717429 · Wang, Ruoyu, Fang, Shaoheng, Huang, Qixing et al.2025 · 36 citationsJournal of chemical theory and computation. 2025;21(15):7628-7635

FedRSU: Federated Learning for Scene Flow Estimation on Roadside Units2401.12862v2 · Shaoheng Fang, Rui Ye, Wenhao Wang et al.2024 · 9 citationsarXiv

Self-Supervised Bird's Eye View Motion Prediction with Cross-Modality Signals2401.11499v1 · Shaoheng Fang, Zuhong Liu, Mingyu Wang et al.2024 · 6 citationsarXiv

TBP-Former: Learning Temporal Bird's-Eye-View Pyramid for Joint Perception and Prediction in Vision-Centric Autonomous Driving2303.09998v2 · Shaoheng Fang, Zi Wang, Yiqi Zhong et al.2023 · 38 citationsarXiv

Where2comm: Communication-Efficient Collaborative Perception via Spatial Confidence Maps2209.12836v1 · Yue Hu, Shaoheng Fang, Zixing Lei et al.2022 · 178 citationsarXiv

Aerial Monocular 3D Object Detection2208.03974v2 · Yue Hu, Shaoheng Fang, Weidi Xie et al.2022 · 35 citationsarXiv

Career total: 9 works. 8 are in this corpus.

Profile built from the corpus for this byline.

Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.