collaborators

6 papers

cs.CV2026

Concept-based Adversarial Attack: a Probabilistic Perspective

Andi Zhang, Xuan Ding, Steven McDonagh +1

We propose a concept-based adversarial attack framework that extends beyond single-image perturbations by adopting a probabilistic perspective. Rather than modifying a single image…

cs.CL2026

Hierarchical Orthogonal Residual Spread for Precise Massive Editing in Large Language Models

Xiaojie Gu, Guangxu Chen, Yuheng Yang +2

Large language models (LLMs) exhibit exceptional performance across various domains, yet they face critical safety concerns. Model editing has emerged as an effective approach to m…

cs.LG2025

LoKO: Low-Rank Kalman Optimizer for Online Fine-Tuning of Large Models

Hossein Abdi, Mingfei Sun, Andi Zhang +2

Training large models with millions or even billions of parameters from scratch incurs substantial computational costs. Parameter Efficient Fine-Tuning (PEFT) methods, particularly…

cs.CV2025

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

Boming Miao, Chunxiao Li, Xiaoxiao Wang +4

Diffusion models have achieved impressive success in generating photorealistic images, but challenges remain in ensuring precise semantic alignment with input prompts. Optimizing t…

cs.LG2025

Rethinking Inter-LoRA Orthogonality in Adapter Merging: Insights from Orthogonal Monte Carlo Dropout

Andi Zhang, Xuan Ding, Haofan Wang +2

We propose Orthogonal Monte Carlo Dropout, a mechanism that enforces strict orthogonality when combining sparse semantic vectors without extra time complexity. Low-Rank Adaptation…

cs.LG2025

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

Daiheng Gao, Nanxiang Jiang, Andi Zhang +5

Concept erasure techniques have been widely deployed in T2I diffusion models to prevent inappropriate content generation for safety and copyright considerations. However, as models…