| Forget Vectors at Play: Universal Input Perturbations Driving Machine Unlearning in Image Classification | Dec 21, 2024 | image-classificationImage Classification | CodeCode Available | 0 |
| Concept-ROT: Poisoning Concepts in Large Language Models with Model Editing | Dec 17, 2024 | MisinformationModel Editing | CodeCode Available | 0 |
| Model-Editing-Based Jailbreak against Safety-aligned Large Language Models | Dec 11, 2024 | Model EditingSafety Alignment | —Unverified | 0 |
| Unveiling Concept Attribution in Diffusion Models | Dec 3, 2024 | Model Editing | CodeCode Available | 0 |
| Lifelong Knowledge Editing for Vision Language Models with Low-Rank Mixture-of-Experts | Nov 23, 2024 | knowledge editingMixture-of-Experts | —Unverified | 0 |
| Safety Without Semantic Disruptions: Editing-free Safe Image Generation via Context-preserving Dual Latent Reconstruction | Nov 21, 2024 | Image GenerationModel Editing | —Unverified | 0 |
| Model Editing for LLMs4Code: How Far are We? | Nov 11, 2024 | 16kCode Generation | CodeCode Available | 0 |
| Learning Where to Edit Vision Transformers | Nov 4, 2024 | Meta-LearningModel Editing | CodeCode Available | 0 |
| Expose Before You Defend: Unifying and Enhancing Backdoor Defenses via Exposed Models | Oct 25, 2024 | backdoor defenseModel Editing | CodeCode Available | 0 |
| Inference time LLM alignment in single and multidomain preference spectrum | Oct 24, 2024 | Model EditingPrompt Engineering | —Unverified | 0 |
