catastrophic forgetting

SelfAug: Mitigating Catastrophic Forgetting in Retrieval-Augmented Generation via Distribution Self-Alignment EMNLP 2025 Self-Expansion of Pre-trained Models with Mixture of Adapters for Continual Learning CVPR 2025 SLIM: Let LLM Learn More and Forget Less with Soft LoRA and Identity Mixture NAACL 2025 SMoLoRA: Exploring and Defying Dual Catastrophic Forgetting in Continual Visual Instruction Tuning ICCV 2025 Specifying What You Know or Not for Multi-Label Class-Incremental Learning AAAI 2025 Speech-IFEval: Evaluating Instruction-Following and Quantifying Catastrophic Forgetting in Speech-Aware Language Models Interspeech 2025 SSR: Alignment-Aware Modality Connector for Speech Language Models ACL 2025 Stacked LoRA: Isolated Low-Rank Adaptation for Lifelong Knowledge Management IJCNLP 2025 Stacking Brick by Brick: Aligned Feature Isolation for Incremental Face Forgery Detection CVPR 2025 STAR: Stability-Inducing Weight Perturbation for Continual Learning ICLR 2025 Synthetic Data is an Elegant GIFT for Continual Vision-Language Models CVPR 2025 Systematic Knowledge Injection into Large Language Models via Diverse Augmentation for Domain-Specific RAG NAACL 2025 Temporal Information Retrieval via Time-Specifier Model Merging ACL 2025 Text2Data: Low-Resource Data Generation with Textual Control AAAI 2025 The AdEMAMix Optimizer: Better, Faster, Older ICLR 2025 The Importance of Being Lazy: Scaling Limits of Continual Learning ICML 2025 The Inter-Intra Modal Measure: A Predictive Lens on Fine-Tuning Outcomes in Vision-Language Models ICCV 2025 Theory on Mixture-of-Experts in Continual Learning ICLR 2025 Thinking Fast and Slow: Robust Speech Recognition via Deep Filter-Tuning Interspeech 2025 TiC-LM: A Web-Scale Benchmark for Time-Continual LLM Pretraining ACL 2025 Towards Robust Incremental Learning Under Ambiguous Supervision IJCAI 2025 Towards Unbiased Continual Learning: Avoiding Forgetting in the Presence of Spurious Correlations WACV 2025 Towards Understanding Catastrophic Forgetting in Two-layer Convolutional Neural Networks ICML 2025 Towards Understanding Multi-Task Learning (Generalization) of LLMs via Detecting and Exploring Task-Specific Neurons COLING 2025 Tripartite Weight-Space Ensemble for Few-Shot Class-Incremental Learning CVPR 2025