Tianyu Wang

10

Papers

73

Total Citations

Papers (10)

3D-LLaVA: Towards Generalist 3D LMMs with Omni Superpoint Transformer

Generative Video Propagation

ObjectMover: Generative Object Movement with Video Prior

HOP: Heterogeneous Topology-based Multimodal Entanglement for Co-Speech Gesture Generation

CAP-Net: A Unified Network for 6D Pose and Size Estimation of Categorical Articulated Parts from a Single RGB-D Image

MetaShadow: Object-Centered Shadow Detection, Removal, and Synthesis

DCHM: Depth-Consistent Human Modeling for Multiview Detection

Winnie: Task-Oriented Dialog System with Structure-Aware Contrastive Learning and Enhanced Policy Planning

Mining Supervision for Dynamic Regions in Self-Supervised Monocular Depth Estimation

Geometry-Calibrated DRO: Combating Over-Pessimism with Free Energy Implications