Hao Zhao

Light-X: Generative 4D Video Rendering with Camera and Illumination Control

Light of Normals: Unified Feature Representation for Universal Photometric Stereo

CubeBench: Diagnosing Interactive, Long-Horizon Physical Intelligence under Partial Observations

Next-Scale Autoregressive Models are Zero-Shot Single-Image Object View Synthesizers

RelitTrellis: Lightning-homogenized Structured 3D Latents For Relightable 3D Generation

Stability Under Scrutiny: Benchmarking Representation Paradigms for Online HD Mapping

DanceTogether: Generating Interactive Multi-Person Video without Identity Drifting

ArtHOI: Articulated Human-Object Interaction Synthesis via Dynamics Distillation

Feedforward 4D Reconstruction for Dynamic Driving Scenes using Unposed Images

Sim2Real-HOI: Sim-to-Real HOI Video Generation via Decoupled Motion–Appearance Diffusion

Hybrid Spatial Representations for Species Distribution Modeling

Unifying Appearance Codes and Bilateral Grids for Driving Scene Gaussian Splatting

Ctrl-U: Robust Conditional Image Generation via Uncertainty-aware Reward Modeling

Hybrid Spatial Representations for Species Distribution Modeling

SPA: Enhancing 3D Multimodal LLMs with Mask-based Streamlining Preference Alignment

RGM: Reconstructing High-fidelity 3D Car Assets with Relightable 3D-GS Generative Model from a Single Image