Qingdong He

IVEBench: Modern Benchmark Suite for Instruction-Guided Video Editing Assessment

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

Reasoning to Edit: Hypothetical Instruction-Based Image Editing with Visual Reasoning

The devil is in the details: Enhancing Video Virtual Try-On via Keyframe-Driven Details Injection

Align Human Camouflaged Perception: Visual Refocus Reinforcement Fine-Tuning

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

KAN or MLP? Point Cloud Shows the Way Forward

MMSeg: Multi-Modal and Multi-View Driven Semantic Enrichment for Training-Free Image Prompt Segmentation

TokenAR: Multiple Subject Generation via Autoregressive Token-level enhancement

HumanVideo-MME: Benchmarking MLLMs for Human-Centric Video Understanding

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

PointSeg: A Training-Free Paradigm for 3D Scene Segmentation via Foundation Models

A Comprehensive Library for Benchmarking Multi-class Visual Anomaly Detection