Huaizu Jiang

XFacta: Contemporary, Real-World Dataset and Evaluation for Multimodal Misinformation Detection with Multimodal LLMs

Absolute Coordinates Make Motion Generation Easy

Struct2D: A Perception-Guided Framework for Spatial Reasoning in MLLMs

SV4D: Dynamic 3D Content Generation with Multi-Frame and Multi-View Consistency

HouseCrafter: Lifting Floorplans to 3D Scenes with 2D Diffusion Model

HOI-Diff: Text-Driven Synthesis of 3D Human-Object Interactions using Diffusion Models