Continual Learning

Temporal Flexibility in Spiking Neural Networks: Towards Generalization Across Time Steps and Deployment Friendliness ICLR 2025 Temporal Information Retrieval via Time-Specifier Model Merging ACL 2025 Theory on Mixture-of-Experts in Continual Learning ICLR 2025 The Right Time Matters: Data Arrangement Affects Zero-Shot Generalization in Instruction Tuning ACL 2025 Think and Recall: Layer-Level Prompting for Lifelong Model Editing EMNLP 2025 Think Small, Act Big: Primitive Prompt Learning for Lifelong Robot Manipulation CVPR 2025 Think Twice Before Adaptation: Improving Adaptability of DeepFake Detection via Online Test-Time Adaptation IJCAI 2025 TinySubNets: An Efficient and Low Capacity Continual Learning Strategy AAAI 2025 Towards Continual Universal Segmentation CVPR 2025 Towards Continuous Reuse of Graph Models via Holistic Memory Diversification ICLR 2025 Towards Effective and Efficient Continual Pre-training of Large Language Models ACL 2025 Towards Macro-AUC Oriented Imbalanced Multi-Label Continual Learning AAAI 2025 Towards Robust Incremental Learning Under Ambiguous Supervision IJCAI 2025 Towards Robust Sentiment Analysis of Temporally-Sensitive Policy-Related Online Text ACL 2025 Towards Unbiased and Robust Spatio-Temporal Scene Graph Generation and Anticipation CVPR 2025 Towards Unbiased Continual Learning: Avoiding Forgetting in the Presence of Spurious Correlations WACV 2025 Towards Understanding Multi-Task Learning (Generalization) of LLMs via Detecting and Exploring Task-Specific Neurons COLING 2025 Training Consistent Mixture-of-Experts-Based Prompt Generator for Continual Learning AAAI 2025 Tripartite Weight-Space Ensemble for Few-Shot Class-Incremental Learning CVPR 2025 UNLEARN Efficient Removal of Knowledge in Large Language Models NAACL 2025 Unlocking the Power of Function Vectors for Characterizing and Mitigating Catastrophic Forgetting in Continual Instruction Tuning ICLR 2025 Unsupervised Continual Domain Shift Learning with Multi-Prototype Modeling CVPR 2025 Unveiling and Addressing Pseudo Forgetting in Large Language Models ACL 2025 Velocitune: A Velocity-based Dynamic Domain Reweighting Method for Continual Pre-training ACL 2025 Vision and Language Synergy for Rehearsal Free Continual Learning ICLR 2025