Peng Gao

Decoupled DMD: CFG Augmentation as the Spear, Distribution Matching as the Shield

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

Contrastive Self-Rewarding MLLM

Visionary-R1: Mitigating Shortcuts in Visual Reasoning with Reinforcement Learning

EnerVerse: Envisioning Embodied Future Space for Robotics Manipulation

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

MAVIS: Mathematical Visual Instruction Tuning with an Automatic Data Engine

MMSearch: Unveiling the Potential of Large Models as Multi-modal Search Engines

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

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

Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You Want

MME-CoT: Benchmarking Chain-of-Thought in Large Multimodal Models for Reasoning Quality, Robustness, and Efficiency

LongHalQA: Long-Context Hallucination Evaluation for MultiModal Large Language Models

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

VEnhancer: Generative Space-Time Enhancement for Video Generation

AR-1-to-3: Single Image to Consistent 3D Object Generation via Next-View Prediction

Customize Your Visual Autoregressive Recipe with Set Autoregressive Modeling

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

TerDiT: Ternary Diffusion Models with Transformers

EfficientQAT: Efficient Quantization-Aware Training for Large Language Models