Yan Zhang

MUIQD: Benchmarking and Facilitating Multimodal LLMs for Underwater Image Quality Perception

FlexibleLLM: Making Low-Bit Quantization for Large Language Models More Flexible and Efficient

Event-Anchored Frame Selection for Efficient Long-Video Understanding

Breaking the Bias: Quantifying the Attention of Industrial Anomaly Detection

HGT-UCOD: A Hint-Guided Teacher Framework for Unsupervised Camouflaged Object Detection

FlatPose: An Upsampling-Free Transformer for Human Pose Estimation

LIQT: Bridging Liquid Neural Dynamics and Human Perceptual Mechanisms for Blind Image Quality Assessment

FOLD: Fast Correct Speculative Decoding

Modality-Aware Quantization: Balancing Visual and Textual Fidelity in Multimodal Compression

Pseudo-Label Supervision in Unsupervised Industrial Anomaly Detection

Zooming from Context to Cue: Hierarchical Preference Optimization for Multi-Image MLLMs

UniQA: Unified Vision-Language Pre-training for Image Quality and Aesthetic Assessment

Gamma: Toward Generic Image Assessment with Mixture of Assessment Experts

Less is More: Learning Reference Knowledge Using No-Reference Image Quality Assessment