Yitong Wang

12

Papers

130

Total Citations

Papers (12)

CreatiLayout: Siamese Multimodal Diffusion Transformer for Creative Layout-to-Image Generation

Universal Segmentation at Arbitrary Granularity with Language Instruction

LLMGA: Multimodal Large Language Model based Generation Assistant

DreamOmni: Unified Image Generation and Editing

ByteEdit: Boost, Comply and Accelerate Generative Image Editing

DreamFuse: Adaptive Image Fusion with Diffusion Transformer

DreamLayer: Simultaneous Multi-Layer Generation via Diffusion Model

Stepping Out of Similar Semantic Space for Open-Vocabulary Segmentation

EntityErasure: Erasing Entity Cleanly via Amodal Entity Segmentation and Completion

Fast Omni-Directional Image Super-Resolution: Adapting the Implicit Image Function with Pixel and Semantic-Wise Spherical Geometric Priors

QK-Edit: Revisiting Attention-based Injection in MM-DiT for Image and Video Editing

Open-Vocabulary Segmentation with Semantic-Assisted Calibration