Showing 2025Show all
3 papers · 1 filter
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…
cs.CV2025
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…