Nenghai Yu

17

Papers

443

Total Citations

Papers (17)

OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation

TCI-Former: Thermal Conduction-Inspired Transformer for Infrared Small Target Detection

Unifying Multi-Modal Uncertainty Modeling and Semantic Alignment for Text-to-Image Person Re-identification

Data-Free Hard-Label Robustness Stealing Attack

FaceRSA: RSA-Aware Facial Identity Cryptography Framework

UNICL-SAM: Uncertainty-Driven In-Context Segmentation with Part Prototype Discovery

Scale Your Instructions: Enhance the Instruction-Following Fidelity of Unified Image Generation Model by Self-Adaptive Attention Scaling

Rethinking Masked Data Reconstruction Pretraining for Strong 3D Action Representation Learning

FE-CLIP: Frequency Enhanced CLIP Model for Zero-Shot Anomaly Detection and Segmentation

MuST: Robust Image Watermarking for Multi-Source Tracing

Deciphering Cross-Modal Alignment in Large Vision-Language Models via Modality Integration Rate

Towards More Unified In-context Visual Understanding

Gaussian Shading: Provable Performance-Lossless Image Watermarking for Diffusion Models

AquaLoRA: Toward White-box Protection for Customized Stable Diffusion Models via Watermark LoRA

Training-free Open-Vocabulary Semantic Segmentation via Diverse Prototype Construction and Sub-region Matching

Transferable Facial Privacy Protection against Blind Face Restoration via Domain-Consistent Adversarial Obfuscation

TAG-WM: Tamper-Aware Generative Image Watermarking via Diffusion Inversion Sensitivity