knowledge preservation

Editing Is a Bargaining Game: Balanced Knowledge Editing in Large Language Models AAAI 2026 LoKI: Low-Damage Knowledge Implanting of Large Language Models AAAI 2026 Prompt-OT: An Optimal Transport Regularization Paradigm for Knowledge Preservation in Vision-Language Model Adaptation WACV 2026 Safe Vision-Language Models via Unsafe Weights Manipulation WACV 2026 Achieving More with Less: Additive Prompt Tuning for Rehearsal-Free Class-Incremental Learning ICCV 2025 ComprehendEdit: A Comprehensive Dataset and Evaluation Framework for Multimodal Knowledge Editing AAAI 2025 Constraining Sequential Model Editing with Editing Anchor Compression NAACL 2025 DPCore: Dynamic Prompt Coreset for Continual Test-Time Adaptation ICML 2025 GeoEdit: Geometric Knowledge Editing for Large Language Models EMNLP 2025 HiDe-LLaVA: Hierarchical Decoupling for Continual Instruction Tuning of Multimodal Large Language Model ACL 2025 LyapLock: Bounded Knowledge Preservation in Sequential Large Language Model Editing EMNLP 2025 MMUnlearner: Reformulating Multimodal Machine Unlearning in the Era of Multimodal Large Language Models ACL 2025 Progressive Homeostatic and Plastic Prompt Tuning for Audio-Visual Multi-Task Incremental Learning ICCV 2025 Propulsion: Steering LLM with Tiny Fine-Tuning COLING 2025 Task-Agnostic Guided Feature Expansion for Class-Incremental Learning CVPR 2025 Accurate Retraining-free Pruning for Pretrained Encoder-based Language Models ICLR 2024 CorDA: Context-Oriented Decomposition Adaptation of Large Language Models for Task-Aware Parameter-Efficient Fine-tuning NeurIPS 2024 Knowledge-Preserving Pluggable Modules for Multilingual Speech Translation Tasks Interspeech 2024 Merge to Learn: Efficiently Adding Skills to Language Models with Model Merging EMNLP 2024 Pruning via Merging: Compressing LLMs via Manifold Alignment Based Layer Merging EMNLP 2024 Cross-lingual Continual Learning ACL 2023 Self-regulating Prompts: Foundational Model Adaptation without Forgetting ICCV 2023 The Cost of Compression: Investigating the Impact of Compression on Parametric Knowledge in Language Models EMNLP 2023 Adapting a Language Model While Preserving its General Knowledge EMNLP 2022 From Dense to Sparse: Contrastive Pruning for Better Pre-trained Language Model Compression AAAI 2022