Lingjuan Lyu

22

Papers

241

Total Citations

Papers (22)

Detecting, Explaining, and Mitigating Memorization in Diffusion Models

Unveiling and Mitigating Memorization in Text-to-image Diffusion Models through Cross Attention

Stretching Each Dollar: Diffusion Training from Scratch on a Micro-Budget

FedMef: Towards Memory-efficient Federated Dynamic Pruning

MLLM-as-a-Judge for Image Safety without Human Labeling

A Simple Background Augmentation Method for Object Detection with Diffusion Model

CO-SPY: Combining Semantic and Pixel Features to Detect Synthetic Images by AI

Unlearning through Knowledge Overwriting: Reversible Federated Unlearning via Selective Sparse Adapter

FlowerTune: A Cross-Domain Benchmark for Federated Fine-Tuning of Large Language Models

Exploit Gradient Skewness to Circumvent Byzantine Defenses for Federated Learning

Six-CD: Benchmarking Concept Removals for Text-to-image Diffusion Models

StelLA: Subspace Learning in Low-rank Adaptation using Stiefel Manifold

MixA: A Mixed Attention approach with Stable Lightweight Linear Attention to enhance Efficiency of Vision Transformers at the Edge

Rethinking Byzantine Robustness in Federated Recommendation from Sparse Aggregation Perspective

Personalized Federated Learning under Local Supervision

Argus: A Compact and Versatile Foundation Model for Vision

Revisiting Source-Free Domain Adaptation: Insights into Representativeness, Generalization, and Variety

How to Trace Latent Generative Model Generated Images without Artificial Watermark?

Bridging Model Heterogeneity in Federated Learning via Uncertainty-based Asymmetrical Reciprocity Learning

PerceptAnon: Exploring the Human Perception of Image Anonymization Beyond Pseudonymization for GDPR

Effective Federated Graph Matching

COALA: A Practical and Vision-Centric Federated Learning Platform