9 papers
LoRango: It Takes Two LoRAs to Unlock Hidden Behaviors in Diffusion Models
Jin Wei, Rundong Li, Ruihao Yang +10
Users commonly combine multiple Low-Rank Adaptation (LoRA) adapters to personalize images with different subjects, styles, and visual attributes. Yet inspecting adapters individual…
A Trustworthy Watermarking Framework for LLM-Generated Food Safety Content
Zhongli Fang, Yiran Chen, Lingyun Zhang +4
Large language models are transforming many industries with their text generation abilities. However, their outputs can be easily tampered with, creating serious risks in critical…
TAOT: Topology-Aware Optimal Transport for Dynamic Expert Replica Placement in MoE Training
Lingyun Zhang, Henghua Zhang, Shilei Gu +5
Mixture-of-Experts (MoE) has become a key architecture for scaling large language models (LLMs), yet its dynamic routing causes severe load imbalance in expert-parallel training. E…
SafeCtrl: Region-Aware Safety Control for Text-to-Image Diffusion via Detect-Then-Suppress
Lingyun Zhang, Yu Xie, Zhongli Fang +2
The widespread deployment of text-to-image diffusion models is significantly challenged by the generation of visually harmful content, such as sexually explicit content, violence,…
IdentityGuard: Context-Aware Restriction and Provenance for Personalized Synthesis
Lingyun Zhang, Yu Xie, Ping Chen
The nature of personalized text-to-image models poses a unique safety challenge that generic context-blind methods are ill-equipped to handle. Such global filters create a dilemma:…
SafeCtrl: Region-Based Safety Control for Text-to-Image Diffusion via Detect-Then-Suppress
Lingyun Zhang, Yu Xie, Yanwei Fu +1
The widespread deployment of text-to-image models is challenged by their potential to generate harmful content. While existing safety methods, such as prompt rewriting or model fin…
NSFW-Classifier Guided Prompt Sanitization for Safe Text-to-Image Generation
Yu Xie, Chengjie Zeng, Lingyun Zhang +1
The rapid advancement of text-to-image (T2I) models, such as Stable Diffusion, has enhanced their capability to synthesize images from textual prompts. However, this progress also…
Concept Replacer: Replacing Sensitive Concepts in Diffusion Models via Precision Localization
Lingyun Zhang, Yu Xie, Yanwei Fu +1
As large-scale diffusion models continue to advance, they excel at producing high-quality images but often generate unwanted content, such as sexually explicit or violent content.…
HARE: HumAn pRiors, a key to small language model Efficiency
Lingyun Zhang, Bin jin, Gaojian Ge +7
Human priors play a crucial role in efficiently utilizing data in deep learning. However, with the development of large language models (LLMs), there is an increasing emphasis on s…