Lei Zhang

17 papers International Digital Economy Academy (IDEA)

• BurstDeflicker: A Benchmark Dataset for Flicker Removal in Dynamic Scenes
• DNAEdit: Direct Noise Alignment for Text-Guided Rectified Flow Editing
• DP²O-SR: Direct Perceptual Preference Optimization for Real-World Image Super-Resolution
• Do LVLMs Truly Understand Video Anomalies? Revealing Hallucination via Co-Occurrence Patterns
• GPSToken: Gaussian Parameterized Spatially-adaptive Tokenization for Image Representation and Generation
• InstructRestore: Region-Customized Image Restoration with Human Instructions
• MIRAGE: Assessing Hallucination in Multimodal Reasoning Chains of MLLM
• MobileODE: An Extra Lightweight Network
• One-Step Diffusion for Detail-Rich and Temporally Consistent Video Super-Resolution
• OpenOmni: Advancing Open-Source Omnimodal Large Language Models with Progressive Multimodal Alignment and Real-time Emotional Speech Synthesis
• PASS: Path-selective State Space Model for Event-based Recognition
• Perceive Anything: Recognize, Explain, Caption, and Segment Anything in Images and Videos
• Polyline Path Masked Attention for Vision Transformer
• Registration is a Powerful Rotation-Invariance Learner for 3D Anomaly Detection
• Rethinking Out-of-Distribution Detection and Generalization with Collective Behavior Dynamics
• The Underappreciated Power of Vision Models for Graph Structural Understanding
• VisualQuality-R1: Reasoning-Induced Image Quality Assessment via Reinforcement Learning to Rank