Siyu Zhu

Large Depth Completion Model from Sparse Observations

LaTo: Landmark-tokenized Diffusion Transformer for Fine-grained Human Face Editing

Forge4D: Feed-Forward 4D Human Reconstruction and Interpolation from Uncalibrated Sparse Videos

LHM++: An Efficient Large Human Reconstruction Model for Pose-free Images to 3D

Pyramid Patchification Flow for Visual Generation

PanoLAM: Large Avatar Model for Gaussian Full-Head Synthesis from One-shot Unposed Image

Head-wise Adaptive Rotary Positional Encoding for Fine-Grained Image Generation

OmniMotion: Multimodal Motion Generation with Continuous Masked Autoregression

MCM: Multi-layer Concept Map for Efficient Concept Learning from Masked Images

MolReasoner: Toward Effective and Interpretable Reasoning for Molecular LLMs

Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention

Flow Distillation Sampling: Regularizing 3D Gaussians with Pre-trained Matching Priors

Hallo2: Long-Duration and High-Resolution Audio-Driven Portrait Image Animation

VideoMV: Consistent Multi-View Generation Based on Large Video Generative Model