Xiaohong Liu

22

Papers

463

Total Citations

Papers (22)

Improving Video Generation with Human Feedback

LightenDiffusion: Unsupervised Low-Light Image Enhancement with Latent-Retinex Diffusion Models

Towards Open-ended Visual Quality Comparison

Lumina-Image 2.0: A Unified and Efficient Image Generative Framework

A-Bench: Are LMMs Masters at Evaluating AI-generated Images?

Rethinking Vision-Language Model in Face Forensics: Multi-Modal Interpretable Forged Face Detector

Low-Light Image Enhancement via Generative Perceptual Priors

Learning Hazing to Dehazing: Towards Realistic Haze Generation for Real-World Image Dehazing

RoboFactory: Exploring Embodied Agent Collaboration with Compositional Constraints

TR-PTS: Task-Relevant Parameter and Token Selection for Efficient Tuning

CoPRA: Bridging Cross-domain Pretrained Sequence Models with Complex Structures for Protein-RNA Binding Affinity Prediction

MoEdit: On Learning Quantity Perception for Multi-object Image Editing

Who is a Better Talker: Subjective and Objective Quality Assessment for AI-Generated Talking Heads

Perception-Oriented Video Frame Interpolation via Asymmetric Blending

Samba: A Unified Mamba-based Framework for General Salient Object Detection

Image Quality Assessment: From Human to Machine Preference

Q-Eval-100K: Evaluating Visual Quality and Alignment Level for Text-to-Vision Content

UniSTD: Towards Unified Spatio-Temporal Learning across Diverse Disciplines

Information Density Principle for MLLM Benchmarks

Learning to See in the Extremely Dark

Text2QR: Harmonizing Aesthetic Customization and Scanning Robustness for Text-Guided QR Code Generation

Q-Bench-Video: Benchmark the Video Quality Understanding of LMMs