Zheng Ge

6

Papers

462

Total Citations

Papers (6)

DreamLLM: Synergistic Multimodal Comprehension and Creation

ShapeLLM: Universal 3D Object Understanding for Embodied Interaction

Reconstructive Visual Instruction Tuning

Taming Teacher Forcing for Masked Autoregressive Video Generation

Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoning

Perception in Reflection