Le Zhuo

Factuality Matters: When Image Generation and Editing Meet Structured Visuals

PICABench: How Far are We from Physical Realistic Image Editing?

ProteinAE: Protein Diffusion Autoencoders for Structure Encoding

Lumina-OmniLV: A Unified Multimodal Framework for General Low-Level Vision

Lightning Video: Building Compact Diffusion Transformers for High-Fidelity On-Device Video Generation

T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT

Lumina-T2X: Scalable Flow-based Large Diffusion Transformer for Flexible Resolution Generation

LLaVA-MoD: Making LLaVA Tiny via MoE-Knowledge Distillation

Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

PixWizard: Versatile Image-to-Image Visual Assistant with Open-Language Instructions

I-Max: Maximize the Resolution Potential of Pre-trained Rectified Flow Transformers with Projected Flow

Customize Your Visual Autoregressive Recipe with Set Autoregressive Modeling

Exploring the Design Space of Autoregressive Models for Efficient and Scalable Image Generation