model editing

Attribution-Guided Model Rectification of Unreliable Neural Network Behaviors CVPR 2026 Closed-Form Concept Erasure via Double Projections CVPR 2026 Deep Model Reuse: Paving the Way for Efficient and Generalizable AI Systems AAAI 2026 Diagnosing Hidden Instabilities in Model Editing via Uncertainty Quantification ACL 2026 Editing the Moving World: Model Editing for Video LLMs ACL 2026 Escaping Optimization Stagnation: Taking Steps Beyond Task Arithmetic via Difference Vectors AAAI 2026 From Weights to Concepts: Data-Free Interpretability of CLIP via Singular Vector Decomposition CVPR 2026 HiEdit: Lifelong Model Editing with Hierarchical Reinforcement Learning ACL 2026 Model Editing as a Double-Edged Sword: Steering Agent Behavior Toward Beneficence or Harm AAAI 2026 PATCH: Mitigating PII Leakage in Language Models with Privacy-Aware Targeted Circuit PatcHing EACL 2026 Personality Editing for Language Models through Adjusting Self-Referential Queries EACL 2026 SAME: Safety-Aware Model Editing Guided by Safety Transformation ACL 2026 SAME: Sparse and Anchored Model Editing for Heterogeneous Incremental Learning under Limited Data CVPR 2026 ShadeEdit: A Utility-Preserving and Defense-Evasive Knowledge Manipulation Attack in Federated LLMs AAAI 2026 When Privacy Meets Recovery: The Overlooked Half of Surrogate-Driven Privacy Preservation for MLLM Editing AAAI 2026 A Causal Lens for Evaluating Faithfulness Metrics EMNLP 2025 ACE: Anti-Editing Concept Erasure in Text-to-Image Models CVPR 2025 AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models ICLR 2025 Answer When Needed, Forget When Not: Language Models Pretend to Forget via In-Context Knowledge Unlearning ACL 2025 Attribution Analysis Meets Model Editing: Advancing Knowledge Correction in Vision Language Models with VisEdit AAAI 2025 BalancEdit: Dynamically Balancing the Generality-Locality Trade-off in Multi-modal Model Editing ICML 2025 BiasEdit: Debiasing Stereotyped Language Models via Model Editing NAACL 2025 Breaking Boundaries: Investigating the Effects of Model Editing on Cross-linguistic Performance NAACL 2025 Bring Your Own Knowledge: A Survey of Methods for LLM Knowledge Expansion ACL 2025 Can Knowledge Editing Really Correct Hallucinations? ICLR 2025