Gang YU

SpeakerVid-5M: A Large-Scale High-Quality Dataset for Audio-Visual Dyadic Interactive Human Generation

IGGT: Instance-Grounded Geometry Transformer for Semantic 3D Reconstruction

WithAnyone: Toward Controllable and ID Consistent Image Generation

LazyDrag: Enabling Stable Drag-Based Editing on Multi-Modal Diffusion Transformers via Explicit Correspondence

RegionE: Adaptive Region-Aware Generation for Efficient Image Editing

In-Context Learning with Unpaired Clips for Instruction-based Video Editing

UniVerse-1: Unified Audio-Video Generation via Stitching of Experts

Training-Free Text-Guided Color Editing with Multi-Modal Diffusion Transformer

ARGOS: Hierarchical Autoregressive Generation of Unbounded 3D Outdoor Scenes with High Fidelity and Spatial Control

ReasonEdit: Towards Reasoning-Enhanced Image Editing Models

Native 3D Editing with Full Attention

OmniSVG: A Unified Scalable Vector Graphics Generation Model

MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers

Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Generation

Causal Motion Tokenizer for Streaming Motion Generation

MVPaint: 3D Texture Generation with Multi-View Consistency