Pin Tang, Guoqing Wang, Xiangxuan Ren, Zhongdao Wang, Guodongfang Zhao, Bailan Feng, Chao Ma

Scalable sensor-agnostic image-plane perception and planning with deterministic 3D trajectory lifting and dense intermediate GRPO rewards.

Guoqing Wang, Pin Tang, Xiangxuan Ren, Guodongfang Zhao, Bailan Feng, Chao Ma

Action-conditioned predictive world modeling for multimodal understanding, future reasoning, and autonomous-driving planning.

Guoqing Wang, Pin Tang, Xiangxuan Ren, Chao Ma

Separating changes caused by the moving observer from changes in the scene lets an occupancy world model learn residual dynamics and preserve consistency over longer forecasts.

Haoyu Zhao, Zihao Zhang, Jiaxi Gu, Haoran Chen, Qingping Zheng, Pin Tang, Yeyin Jin, Yuang Zhang, Junqi Cheng, Zenghui Lu, Peng Shu, Zuxuan Wu, Yu-Gang Jiang

Transfers spatial reasoning from vision-language-camera models to controllable video generation.

Xiangxuan Ren, Zhongdao Wang, Liping Hou, Pin Tang, Guoqing Wang, Chao Ma

A token-based formulation for grounding diverse entities in multimodal large language models.

Pin Tang, Zhongdao Wang, Guoqing Wang, Xiangxuan Ren, Chao Ma

Separates scene completion from semantic prediction using sparse signed-distance fields and geometry-guided propagation for accurate, efficient occupancy prediction.

Guoqing Wang, Pin Tang, Xiangxuan Ren, Liping Hou, Chao Ma

Targeted completion for reconstructing driving scenes from sparse camera observations.

Pin Tang, Zhongdao Wang, Guoqing Wang, Jilai Zheng, Xiangxuan Ren, Bailan Feng, Chao Ma

A sparse latent representation that reduces FLOPs by 74.9% while improving semantic occupancy mIoU from 12.8% to 14.1%.

Guoqing Wang, Zhongdao Wang, Pin Tang, Jilai Zheng, Xiangxuan Ren, Bailan Feng, Chao Ma

Generative multimodal modeling for semantic 3D occupancy prediction in driving scenes.

Jilai Zheng, Pin Tang, Zhongdao Wang, Guoqing Wang, Xiangxuan Ren, Bailan Feng, Chao Ma

Enhances occupancy prediction with semantic knowledge encoded by language vocabulary.

Xiangxuan Ren, Zhongdao Wang, Pin Tang, Guoqing Wang, Jilai Zheng, Chao Ma

Lightweight geometric adaptation enhances camera-based 3D detection with LiDAR cues while preserving camera-only operation.

Jilai Zheng, Pin Tang, Xiangxuan Ren, Zhongdao Wang, Chao Ma

Bi-stream knowledge transfer for learning 3D point-cloud detectors from limited annotations.

Pin Tang, Hai-Ming Xu, Chao Ma

Transfers cross-modal prototypes to improve point-cloud semantic segmentation.

Pin Tang, Pinli Yang, Dong Nie, Xi Wu, Jiliu Zhou, Yan Wang

End-to-end medical image segmentation guided by learned predictive uncertainty.

Shuai Tan, Pin Tang, Xingchen Peng, Jianghong Xiao, Chen Zu, Xi Wu, Jiliu Zhou, Yan Wang

Multi-task learning of isodose contours and gradients for radiotherapy dose prediction.

Pin Tang, Chen Zu, Mei Hong, Rui Yan, Xingchen Peng, Jianghong Xiao, Xi Wu, Jiliu Zhou, Luping Zhou, Yan Wang

Dual-attention dense segmentation for automatic head-and-neck tumor delineation in MRI.