Weiming Zhang

ScaleCap: Scalable Image Captioning via Dual-Modality Debiasing

FARI: Robust One-Step Inversion for Watermarking in Diffusion Models

VLMShield: Efficient and Robust Defense of Vision-Language Models against Malicious Prompts

PSRT: Accelerating LRM-based Guard Models via Prefilled Safe Reasoning Traces

Revoking Amnesia: RL-based Trajectory Optimization to Resurrect Erased Concepts in Diffusion Models

MoLD: Fine-Grained Multimodal Risk Assessment via Dynamic Analysis Weights

T2SMark: Balancing Robustness and Diversity in Noise-as-Watermark for Diffusion Models

LD-RoViS: Training-free Robust Video Steganography for Deterministic Latent Diffusion Model

De-AntiFake: Rethinking the Protective Perturbations Against Voice Cloning Attacks

StegoZip: Enhancing Linguistic Steganography Payload in Practice with Large Language Models

STEAD: Robust Provably Secure Linguistic Steganography with Diffusion Language Model

Vector Database Watermarking

EraseAnything: Enabling Concept Erasure in Rectified Flow Transformers

A Closer Look at Machine Unlearning for Large Language Models

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

EditMark: Training-free and Harmless Watermark for Large Language Models

Semantic-Aware Diffusion Model for Sequential Recommendation