I am Dingkang Liang, an incoming Assistant Professor at Huazhong University of Science and Technology. My research interests include autonomous driving, embodied AI, 3D perception, point cloud analysis, dense object analysis, and generative modeling.

Homepage | Google Scholar | CV

• Autonomous driving: Orion , MindDrive , DriveMonkey , UniFuture , HERMES , ToC3D , QTNet

• Embodied AI: GRANT , DOMINO , VAGE-3D

• 3D perception / point cloud analysis: PointMamba , PointGST , DAPT , PointTPA , UniSeg3D , ViTWSS3D , SAM3D , DDS3D

• World Model/Generation: HyDRA , DriVerse , EasyCache

• Dense object analysis: FIDTM , TransCrowd , CLTR , CrowdCLIP , AutoScale , SOOD

• Multimodal and domain-specific scene understanding: NAUTILUS , MINIMA , Monkey

• General vision systems and efficiency: MoE-Jetpack

• Research resources: Awesome-World-Model , Awesome-Visual-Transformer

Pinned repositories below highlight selected projects and recent work.