Continual Learning

NeSyC: A Neuro-symbolic Continual Learner For Complex Embodied Tasks In Open Domains ICLR 2025 Neuroplastic Expansion in Deep Reinforcement Learning ICLR 2025 NIRANTAR: Continual Learning with New Languages and Domains on Real-world Speech Data Interspeech 2025 Prevalence of Negative Transfer in Continual Reinforcement Learning: Analyses and a Simple Baseline ICLR 2025 Rehearsal with Auxiliary-Informed Sampling for Audio Deepfake Detection Interspeech 2025 TiC-LM: A Web-Scale Benchmark for Time-Continual LLM Pretraining ACL 2025 Velocitune: A Velocity-based Dynamic Domain Reweighting Method for Continual Pre-training ACL 2025 Adaptive VIO: Deep Visual-Inertial Odometry with Online Continual Learning CVPR 2024 Artificial Generational Intelligence: Cultural Accumulation in Reinforcement Learning NeurIPS 2024 BAMBINO-LM: (Bilingual-)Human-Inspired Continual Pre-training of BabyLM ACL 2024 Breaking Language Barriers: Cross-Lingual Continual Pre-Training at Scale EMNLP 2024 CoGen: Learning from Feedback with Coupled Comprehension and Generation EMNLP 2024 Coherent Temporal Synthesis for Incremental Action Segmentation CVPR 2024 Collaborative Learning across Heterogeneous Systems with Pre-Trained Models AAAI 2024 Consistent Prompting for Rehearsal-Free Continual Learning CVPR 2024 Continual Learning in the Frequency Domain NeurIPS 2024 Continual Learning on a Diet: Learning from Sparsely Labeled Streams Under Constrained Computation ICLR 2024 Continual Learning with Pre-Trained Models: A Survey IJCAI 2024 Continual-MAE: Adaptive Distribution Masked Autoencoders for Continual Test-Time Adaptation CVPR 2024 Continual Relation Extraction via Sequential Multi-Task Learning AAAI 2024 Convolutional Prompting meets Language Models for Continual Learning CVPR 2024 CPPO: Continual Learning for Reinforcement Learning with Human Feedback ICLR 2024 Dirichlet Continual Learning: Tackling Catastrophic Forgetting in NLP UAI 2024 Dissecting learning and forgetting in language model finetuning ICLR 2024 Divide and not forget: Ensemble of selectively trained experts in Continual Learning ICLR 2024