Yao Zhu

13

Papers

5

Total Citations

Papers (13)

Noise Diffusion for Enhancing Semantic Faithfulness in Text-to-Image Synthesis

Towards Understanding How Knowledge Evolves in Large Vision-Language Models

Enhanced Event-based Dense Stereo via Cross-Sensor Knowledge Distillation

SHIFT: Smoothing Hallucinations by Information Flow Tuning for Multimodal Large Language Models

Bridging the Gap Between Ideal and Real-world Evaluation: Benchmarking AI-Generated Image Detection in Challenging Scenarios

An Efficient Framework for Enhancing Discriminative Models via Diffusion Techniques

ImageNet-E: Benchmarking Neural Network Robustness via Attribute Editing

Towards Understanding the Generative Capability of Adversarially Robust Classifiers

COCO-O: A Benchmark for Object Detectors under Natural Distribution Shifts

Towards Annotation-Free Evaluation: KPAScore for Human Keypoint Detection

High Dynamic Range Video Compression: A Large-Scale Benchmark Dataset and A Learned Bit-depth Scalable Compression Algorithm

Enhance the Visual Representation via Discrete Adversarial Training

Boosting Out-of-distribution Detection with Typical Features