Zheng Ge

10

Papers

428

Total Citations

Papers (10)

DreamLLM: Synergistic Multimodal Comprehension and Creation

ShapeLLM: Universal 3D Object Understanding for Embodied Interaction

Taming Teacher Forcing for Masked Autoregressive Video Generation

Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoning

Perception in Reflection

Dense Teacher: Dense Pseudo-Labels for Semi-Supervised Object Detection

NMS by Representative Region: Towards Crowded Pedestrian Detection by Proposal Pairing

OTA: Optimal Transport Assignment for Object Detection

Implicit Identity Leakage: The Stumbling Block to Improving Deepfake Detection Generalization

MatrixVT: Efficient Multi-Camera to BEV Transformation for 3D Perception