{"total":134,"rows":[{"id":"2302.00487","title":"A Comprehensive Survey of Continual Learning: Theory, Method and Application","created":"2023-01-31","cited_by_count":872,"area":null},{"id":"2204.04799","title":"DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning","created":"2022-04-10","cited_by_count":642,"area":null},{"id":"2404.16789","title":"Continual Learning of Large Language Models: A Comprehensive Survey","created":"2024-04-25","cited_by_count":234,"area":null},{"id":"2208.05592","title":"Patching open-vocabulary models by interpolating weights","created":"2022-08-10","cited_by_count":190,"area":null},{"id":"2303.05118","title":"SLCA: Slow Learner with Classifier Alignment for Continual Learning on a Pre-trained Model","created":"2023-03-09","cited_by_count":180,"area":null},{"id":"2407.06886","title":"Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI","created":"2024-07-09","cited_by_count":179,"area":null},{"id":"2307.02251","title":"RanPAC: Random Projections and Pre-trained Models for Continual Learning","created":"2023-07-05","cited_by_count":164,"area":null},{"id":"2205.12393","title":"Fine-tuned Language Models are Continual Learners","created":"2022-05-24","cited_by_count":156,"area":null},{"id":"2403.08763","title":"Simple and Scalable Strategies to Continually Pre-train Large Language Models","created":"2024-03-13","cited_by_count":127,"area":null},{"id":"2310.07234","title":"Hierarchical Decomposition of Prompt-Based Continual Learning: Rethinking Obscured Sub-optimality","created":"2023-10-11","cited_by_count":121,"area":null},{"id":"2312.08782","title":"Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis","created":"2023-12-14","cited_by_count":103,"area":null},{"id":"2502.02542","title":"OverThink: Slowdown Attacks on Reasoning LLMs","created":"2025-02-04","cited_by_count":96,"area":"lr"},{"id":"2205.09357","title":"Continual Pre-Training Mitigates Forgetting in Language and Vision","created":"2022-05-19","cited_by_count":83,"area":null},{"id":"2501.07278","title":"Lifelong Learning of Large Language Model based Agents: A Roadmap","created":"2025-01-13","cited_by_count":83,"area":"agents"},{"id":"2206.11488","title":"On the Importance and Applicability of Pre-Training for Federated Learning","created":"2022-06-23","cited_by_count":71,"area":null},{"id":"2307.09218","title":"A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learning","created":"2023-07-16","cited_by_count":69,"area":null},{"id":"2406.06391","title":"Towards Lifelong Learning of Large Language Models: A Survey","created":"2024-06-10","cited_by_count":64,"area":null},{"id":"2212.12042","title":"Re-basin via implicit Sinkhorn differentiation","created":"2022-12-22","cited_by_count":62,"area":null},{"id":"2205.00329","title":"Continual Learning with Foundation Models: An Empirical Study of Latent Replay","created":"2022-04-30","cited_by_count":61,"area":null},{"id":"2402.17400","title":"Investigating Continual Pretraining in Large Language Models: Insights and Implications","created":"2024-02-27","cited_by_count":57,"area":null},{"id":"2209.09476","title":"SparCL: Sparse Continual Learning on the Edge","created":"2022-09-20","cited_by_count":55,"area":null},{"id":"2403.08568","title":"Consistent Prompting for Rehearsal-Free Continual Learning","created":"2024-03-13","cited_by_count":54,"area":null},{"id":"2407.14143","title":"Class-Incremental Learning with CLIP: Adaptive Representation Adjustment and Parameter Fusion","created":"2024-07-19","cited_by_count":47,"area":null},{"id":"2405.18653","title":"Recent Advances of Foundation Language Models-based Continual Learning: A Survey","created":"2024-05-28","cited_by_count":46,"area":null},{"id":"2212.04842","title":"PIVOT: Prompting for Video Continual Learning","created":"2022-12-09","cited_by_count":45,"area":null},{"id":"2206.00388","title":"Transfer without Forgetting","created":"2022-06-01","cited_by_count":44,"area":null},{"id":"2405.14124","title":"Mixture of Experts Meets Prompt-Based Continual Learning","created":"2024-05-23","cited_by_count":43,"area":"moe"},{"id":"2312.08977","title":"Weighted Ensemble Models Are Strong Continual Learners","created":"2023-12-14","cited_by_count":42,"area":null},{"id":"2406.01375","title":"D-CPT Law: Domain-specific Continual Pre-Training Scaling Law for Large Language Models","created":"2024-06-03","cited_by_count":41,"area":null},{"id":"2210.06443","title":"On the Effectiveness of Lipschitz-Driven Rehearsal in Continual Learning","created":"2022-10-12","cited_by_count":39,"area":null},{"id":"2210.03482","title":"CLAD: A realistic Continual Learning benchmark for Autonomous Driving","created":"2022-10-07","cited_by_count":36,"area":null},{"id":"2212.09744","title":"DSI++: Updating Transformer Memory with New Documents","created":"2022-12-19","cited_by_count":35,"area":null},{"id":"2404.00986","title":"Make Continual Learning Stronger via C-Flat","created":"2024-04-01","cited_by_count":35,"area":null},{"id":"2210.05549","title":"Continual Training of Language Models for Few-Shot Learning","created":"2022-10-11","cited_by_count":33,"area":null},{"id":"2205.13323","title":"The Effect of Task Ordering in Continual Learning","created":"2022-05-26","cited_by_count":31,"area":null},{"id":"2408.15545","title":"SciLitLLM: How to Adapt LLMs for Scientific Literature Understanding","created":"2024-08-28","cited_by_count":29,"area":null},{"id":"2205.12694","title":"Train Flat, Then Compress: Sharpness-Aware Minimization Learns More Compressible Models","created":"2022-05-25","cited_by_count":20,"area":null},{"id":"2407.05229","title":"HiDe-PET: Continual Learning via Hierarchical Decomposition of Parameter-Efficient Tuning","created":"2024-07-07","cited_by_count":20,"area":null},{"id":"2211.03186","title":"Momentum-based Weight Interpolation of Strong Zero-Shot Models for Continual Learning","created":"2022-11-06","cited_by_count":19,"area":null},{"id":"2407.03994","title":"Unlocking the Potential of Model Merging for Low-Resource Languages","created":"2024-07-04","cited_by_count":19,"area":null},{"id":"2407.16695","title":"Stress-Testing Long-Context Language Models with Lifelong ICL and Task Haystack","created":"2024-07-23","cited_by_count":19,"area":null},{"id":"2303.08207","title":"Is forgetting less a good inductive bias for forward transfer?","created":"2023-03-14","cited_by_count":18,"area":null},{"id":"2305.09144","title":"Retentive or Forgetful? Diving into the Knowledge Memorizing Mechanism of Language Models","created":"2023-05-16","cited_by_count":18,"area":null},{"id":"2506.03320","title":"The Future of Continual Learning in the Era of Foundation Models: Three Key Directions","created":"2025-06-03","cited_by_count":17,"area":null},{"id":"2302.04725","title":"Lightweight Transformers for Clinical Natural Language Processing","created":"2023-02-09","cited_by_count":15,"area":"distill"},{"id":"2407.06992","title":"Robust Neural Information Retrieval: An Adversarial and Out-of-distribution Perspective","created":"2024-07-09","cited_by_count":15,"area":null},{"id":"2504.02107","title":"TiC-LM: A Web-Scale Benchmark for Time-Continual LLM Pretraining","created":"2025-04-02","cited_by_count":15,"area":null},{"id":"2601.18699","title":"Mechanistic Analysis of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning","created":"2026-01-26","cited_by_count":14,"area":"moe"},{"id":"2306.01904","title":"Overcoming the Stability Gap in Continual Learning","created":"2023-06-02","cited_by_count":13,"area":null},{"id":"2205.01586","title":"Simpler is Better: off-the-shelf Continual Learning Through Pretrained Backbones","created":"2022-05-03","cited_by_count":12,"area":null},{"id":"2405.20271","title":"ETHER: Efficient Finetuning of Large-Scale Models with Hyperplane Reflections","created":"2024-05-30","cited_by_count":12,"area":null},{"id":"2409.19245","title":"Forgetting, Ignorance or Myopia: Revisiting Key Challenges in Online Continual Learning","created":"2024-09-28","cited_by_count":12,"area":null},{"id":"2510.14865","title":"Midtraining Bridges Pretraining and Posttraining Distributions","created":"2025-10-16","cited_by_count":12,"area":null},{"id":"2303.01081","title":"Can BERT Refrain from Forgetting on Sequential Tasks? A Probing Study","created":"2023-03-02","cited_by_count":11,"area":null},{"id":"2312.00598","title":"Learning from One Continuous Video Stream","created":"2023-12-01","cited_by_count":11,"area":null},{"id":"2510.17776","title":"Mapping Post-Training Forgetting in Language Models at Scale","created":"2025-10-20","cited_by_count":11,"area":null},{"id":"2404.16612","title":"MuseumMaker: Continual Style Customization without Catastrophic Forgetting","created":"2024-04-25","cited_by_count":10,"area":null},{"id":"2408.08295","title":"SLCA++: Unleash the Power of Sequential Fine-tuning for Continual Learning with Pre-training","created":"2024-08-15","cited_by_count":10,"area":null},{"id":"2602.03702","title":"Anytime Pretraining: Horizon-Free Learning-Rate Schedules with Weight Averaging","created":"2026-02-03","cited_by_count":10,"area":null},{"id":"2605.02105","title":"Sharpness-Aware Pretraining Mitigates Catastrophic Forgetting","created":"2026-05-04","cited_by_count":10,"area":null},{"id":"2408.06663","title":"Amuro and Char: Analyzing the Relationship between Pre-Training and Fine-Tuning of Large Language Models","created":"2024-08-13","cited_by_count":9,"area":null},{"id":"2501.01045","title":"ZeroFlow: Overcoming Catastrophic Forgetting is Easier than You Think","created":"2025-01-02","cited_by_count":9,"area":null},{"id":"2502.04469","title":"Ask and Remember: A Questions-Only Replay Strategy for Continual Visual Question Answering","created":"2025-02-06","cited_by_count":9,"area":null},{"id":"2503.00677","title":"Advancing Prompt-Based Methods for Replay-Independent General Continual Learning","created":"2025-03-02","cited_by_count":9,"area":null},{"id":"2504.01961","title":"Learning from Streaming Video with Orthogonal Gradients","created":"2025-04-02","cited_by_count":9,"area":null},{"id":"2504.02666","title":"BECAME: BayEsian Continual Learning with Adaptive Model MErging","created":"2025-04-03","cited_by_count":9,"area":null},{"id":"2406.14026","title":"Demystifying Language Model Forgetting with Low-rank Example Associations","created":"2024-06-20","cited_by_count":8,"area":null},{"id":"2410.09218","title":"Continual Learning with Neuromorphic Computing: Foundations, Methods, and Emerging Applications","created":"2024-10-11","cited_by_count":8,"area":null},{"id":"2210.07171","title":"SQuAT: Sharpness- and Quantization-Aware Training for BERT","created":"2022-10-13","cited_by_count":7,"area":null},{"id":"2306.10724","title":"Partial Hypernetworks for Continual Learning","created":"2023-06-19","cited_by_count":7,"area":null},{"id":"2310.09436","title":"Sub-network Discovery and Soft-masking for Continual Learning of Mixed Tasks","created":"2023-10-13","cited_by_count":7,"area":null},{"id":"2407.10804","title":"Mix-CPT: A Domain Adaptation Framework via Decoupling Knowledge Learning and Format Alignment","created":"2024-07-15","cited_by_count":7,"area":null},{"id":"2503.02844","title":"Beyond Cosine Decay: On the effectiveness of Infinite Learning Rate Schedule for Continual Pre-training","created":"2025-03-04","cited_by_count":7,"area":null},{"id":"2404.09339","title":"Towards Practical Tool Usage for Continually Learning LLMs","created":"2024-04-14","cited_by_count":6,"area":"agents"},{"id":"2405.18069","title":"An Empirical Analysis of Forgetting in Pre-trained Models with Incremental Low-Rank Updates","created":"2024-05-28","cited_by_count":6,"area":null},{"id":"2305.10713","title":"Flatness-Aware Prompt Selection Improves Accuracy and Sample Efficiency","created":"2023-05-18","cited_by_count":5,"area":null},{"id":"2307.16704","title":"Lookbehind-SAM: k steps back, 1 step forward","created":"2023-07-31","cited_by_count":5,"area":null},{"id":"2310.10184","title":"Continual Generalized Intent Discovery: Marching Towards Dynamic and Open-world Intent Recognition","created":"2023-10-16","cited_by_count":5,"area":null},{"id":"2403.07356","title":"Premonition: Using Generative Models to Preempt Future Data Changes in Continual Learning","created":"2024-03-12","cited_by_count":5,"area":null},{"id":"2503.05029","title":"Continual Pre-training of MoEs: How robust is your router?","created":"2025-03-06","cited_by_count":5,"area":"moe"},{"id":"2209.08010","title":"Causes of Catastrophic Forgetting in Class-Incremental Semantic Segmentation","created":"2022-09-16","cited_by_count":4,"area":null},{"id":"2210.00044","title":"Task Formulation Matters When Learning Continually: A Case Study in Visual Question Answering","created":"2022-09-30","cited_by_count":4,"area":null},{"id":"2210.05561","title":"Schedule-Robust Online Continual Learning","created":"2022-10-11","cited_by_count":4,"area":null},{"id":"2303.14115","title":"Principles of Forgetting in Domain-Incremental Semantic Segmentation in Adverse Weather Conditions","created":"2023-03-24","cited_by_count":4,"area":null},{"id":"2311.00235","title":"Implicit biases in multitask and continual learning from a backward error analysis perspective","created":"2023-11-01","cited_by_count":4,"area":null},{"id":"2406.02428","title":"Harnessing Neural Unit Dynamics for Effective and Scalable Class-Incremental Learning","created":"2024-06-04","cited_by_count":4,"area":null},{"id":"2502.12388","title":"Achieving Upper Bound Accuracy of Joint Training in Continual Learning","created":"2025-02-17","cited_by_count":4,"area":null},{"id":"2207.01562","title":"Progressive Latent Replay for efficient Generative Rehearsal","created":"2022-07-04","cited_by_count":3,"area":null},{"id":"2303.13898","title":"Remind of the Past: Incremental Learning with Analogical Prompts","created":"2023-03-24","cited_by_count":3,"area":null},{"id":"2409.11498","title":"Augment, Drop & Swap: Improving Diversity in LLM Captions for Efficient Music-Text Representation Learning","created":"2024-09-17","cited_by_count":3,"area":null},{"id":"2505.12043","title":"MoL for LLMs: Dual-Loss Optimization to Enhance Domain Expertise While Preserving General Capabilities","created":"2025-05-17","cited_by_count":3,"area":null},{"id":"2505.12245","title":"AFCL: Analytic Federated Continual Learning for Spatio-Temporal Invariance of Non-IID Data","created":"2025-05-18","cited_by_count":3,"area":null},{"id":"2505.15769","title":"Transfer of Structural Knowledge from Synthetic Languages","created":"2025-05-21","cited_by_count":3,"area":null},{"id":"2510.01879","title":"REPAIR: Robust Editing via Progressive Adaptive Intervention and Reintegration","created":"2025-10-02","cited_by_count":3,"area":null},{"id":"2604.17736","title":"IncreFA: Breaking the Static Wall of Generative Model Attribution","created":"2026-04-20","cited_by_count":3,"area":null},{"id":"2310.15694","title":"COPR: Continual Learning Human Preference through Optimal Policy Regularization","created":"2023-10-24","cited_by_count":2,"area":"alignment"},{"id":"2405.17054","title":"Improving Data-aware and Parameter-aware Robustness for Continual Learning","created":"2024-05-27","cited_by_count":2,"area":null},{"id":"2410.05648","title":"Does RoBERTa Perform Better than BERT in Continual Learning: An Attention Sink Perspective","created":"2024-10-08","cited_by_count":2,"area":null},{"id":"2502.19513","title":"Mixtraining: A Better Trade-Off Between Compute and Performance","created":"2025-02-26","cited_by_count":2,"area":null},{"id":"2503.04655","title":"CLDyB: Towards Dynamic Benchmarking for Continual Learning with Pre-trained Models","created":"2025-03-06","cited_by_count":2,"area":null}],"next_cursor":"100"}