Donghao Luo

VTBench: Comprehensive Benchmark Suite Towards Real-World Virtual Try-on Models

Towards One-step Causal Video Generation via Adversarial Self-Distillation

Human-MME: A Holistic Evaluation Benchmark for Human-Centric Multimodal Large Language Models

ShortcutBreaker: Low-Rank Noisy Bottleneck with Global Perturbation Attention for Multi-Class Unsupervised Anomaly Detection

OracleAgent: A Multimodal Reasoning Agent for Oracle Bone Script Research

DynamicControl: Adaptive Condition Selection for Improved Text-to-Image Generation

StyleMaster: Towards Flexible Stylized Image Generation with Diffusion Models

Real&Synthetic Dataset and the Linear Attention in Image Restoration

Enhancing Human Body Generation in Diffusion Models with Dual-Level Prior Knowledge

Combating inherent noise for direct preference optimization