{"total":145,"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":"2208.05592","title":"Patching open-vocabulary models by interpolating weights","created":"2022-08-10","cited_by_count":190,"area":null},{"id":"2112.09153","title":"An Empirical Investigation of the Role of Pre-training in Lifelong Learning","created":"2021-12-16","cited_by_count":134,"area":null},{"id":"2106.01085","title":"Online Coreset Selection for Rehearsal-based Continual Learning","created":"2021-06-02","cited_by_count":117,"area":null},{"id":"2204.03044","title":"Fusing finetuned models for better pretraining","created":"2022-04-06","cited_by_count":110,"area":null},{"id":"2203.11834","title":"Improving Generalization in Federated Learning by Seeking Flat Minima","created":"2022-03-22","cited_by_count":98,"area":null},{"id":"2212.10445","title":"Model Ratatouille: Recycling Diverse Models for Out-of-Distribution Generalization","created":"2022-12-20","cited_by_count":97,"area":null},{"id":"2110.14633","title":"Similarity and Matching of Neural Network Representations","created":"2021-10-27","cited_by_count":78,"area":null},{"id":"2104.07446","title":"Rehearsal revealed: The limits and merits of revisiting samples in continual learning","created":"2021-04-15","cited_by_count":76,"area":null},{"id":"2110.11526","title":"Wide Neural Networks Forget Less Catastrophically","created":"2021-10-21","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":"2402.18865","title":"Analyzing and Reducing Catastrophic Forgetting in Parameter Efficient Tuning","created":"2024-02-29","cited_by_count":60,"area":null},{"id":"2311.11908","title":"Continual Learning: Applications and the Road Forward","created":"2023-11-20","cited_by_count":59,"area":null},{"id":"2302.04863","title":"Knowledge is a Region in Weight Space for Fine-tuned Language Models","created":"2023-02-09","cited_by_count":58,"area":null},{"id":"2109.11369","title":"Recent Advances of Continual Learning in Computer Vision: An Overview","created":"2021-09-23","cited_by_count":55,"area":null},{"id":"2106.03027","title":"Model Zoo: A Growing \"Brain\" That Learns Continually","created":"2021-06-06","cited_by_count":54,"area":null},{"id":"2212.01378","title":"ColD Fusion: Collaborative Descent for Distributed Multitask Finetuning","created":"2022-12-02","cited_by_count":52,"area":null},{"id":"2211.08422","title":"Mechanistic Mode Connectivity","created":"2022-11-15","cited_by_count":50,"area":null},{"id":"2202.00275","title":"Architecture Matters in Continual Learning","created":"2022-02-01","cited_by_count":46,"area":null},{"id":"2207.06543","title":"CoSCL: Cooperation of Small Continual Learners is Stronger than a Big One","created":"2022-07-13","cited_by_count":43,"area":null},{"id":"2312.08977","title":"Weighted Ensemble Models Are Strong Continual Learners","created":"2023-12-14","cited_by_count":42,"area":null},{"id":"2303.09483","title":"Achieving a Better Stability-Plasticity Trade-off via Auxiliary Networks in Continual Learning","created":"2023-03-16","cited_by_count":41,"area":null},{"id":"2305.00316","title":"The Ideal Continual Learner: An Agent That Never Forgets","created":"2023-04-29","cited_by_count":35,"area":null},{"id":"2110.07905","title":"Towards Better Plasticity-Stability Trade-off in Incremental Learning: A Simple Linear Connector","created":"2021-10-15","cited_by_count":34,"area":null},{"id":"2209.13917","title":"A simple but strong baseline for online continual learning: Repeated Augmented Rehearsal","created":"2022-09-28","cited_by_count":32,"area":null},{"id":"2104.12081","title":"How Well Does Self-Supervised Pre-Training Perform with Streaming Data?","created":"2021-04-25","cited_by_count":29,"area":null},{"id":"2211.10445","title":"Building a Subspace of Policies for Scalable Continual Learning","created":"2022-11-18","cited_by_count":28,"area":null},{"id":"2304.11431","title":"A Review of Deep Learning for Video Captioning","created":"2023-04-22","cited_by_count":28,"area":null},{"id":"2603.12228","title":"Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weights","created":"2026-03-12","cited_by_count":28,"area":null},{"id":"2207.07730","title":"How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Composition","created":"2022-07-15","cited_by_count":27,"area":null},{"id":"2208.09734","title":"A Multi-Head Model for Continual Learning via Out-of-Distribution Replay","created":"2022-08-20","cited_by_count":27,"area":null},{"id":"2210.14102","title":"Exploring Mode Connectivity for Pre-trained Language Models","created":"2022-10-25","cited_by_count":26,"area":null},{"id":"2402.03660","title":"On the Emergence of Cross-Task Linearity in the Pretraining-Finetuning Paradigm","created":"2024-02-06","cited_by_count":26,"area":null},{"id":"2310.19103","title":"Proving Linear Mode Connectivity of Neural Networks via Optimal Transport","created":"2023-10-29","cited_by_count":25,"area":null},{"id":"2310.14277","title":"A Survey on Continual Semantic Segmentation: Theory, Challenge, Method and Application","created":"2023-10-22","cited_by_count":21,"area":null},{"id":"2405.20231","title":"The Empirical Impact of Neural Parameter Symmetries, or Lack Thereof","created":"2024-05-30","cited_by_count":21,"area":null},{"id":"2505.10717","title":"A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment","created":"2025-05-15","cited_by_count":20,"area":"alignment"},{"id":"2102.02805","title":"How do Quadratic Regularizers Prevent Catastrophic Forgetting: The Role of Interpolation","created":"2021-02-04","cited_by_count":19,"area":null},{"id":"2202.09826","title":"Continual Learning Beyond a Single Model","created":"2022-02-20","cited_by_count":18,"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":"2305.08702","title":"Recyclable Tuning for Continual Pre-training","created":"2023-05-15","cited_by_count":17,"area":null},{"id":"2106.12772","title":"Task-agnostic Continual Learning with Hybrid Probabilistic Models","created":"2021-06-24","cited_by_count":16,"area":null},{"id":"2311.04898","title":"Two Complementary Perspectives to Continual Learning: Ask Not Only What to Optimize, But Also How","created":"2023-11-08","cited_by_count":16,"area":null},{"id":"2407.13771","title":"Training-Free Model Merging for Multi-target Domain Adaptation","created":"2024-07-18","cited_by_count":15,"area":null},{"id":"2503.00823","title":"Task-Agnostic Guided Feature Expansion for Class-Incremental Learning","created":"2025-03-02","cited_by_count":15,"area":null},{"id":"2110.05169","title":"Learning a subspace of policies for online adaptation in Reinforcement Learning","created":"2021-10-11","cited_by_count":14,"area":null},{"id":"2112.01653","title":"Learning Curves for Continual Learning in Neural Networks: Self-Knowledge Transfer and Forgetting","created":"2021-12-03","cited_by_count":14,"area":null},{"id":"2307.10507","title":"FedSoup: Improving Generalization and Personalization in Federated Learning via Selective Model Interpolation","created":"2023-07-20","cited_by_count":14,"area":null},{"id":"2407.20999","title":"MoFO: Momentum-Filtered Optimizer for Mitigating Forgetting in LLM Fine-Tuning","created":"2024-07-30","cited_by_count":14,"area":null},{"id":"2404.04002","title":"Continual Learning with Weight Interpolation","created":"2024-04-05","cited_by_count":13,"area":null},{"id":"2403.06398","title":"On the Diminishing Returns of Width for Continual Learning","created":"2024-03-11","cited_by_count":12,"area":null},{"id":"2504.18992","title":"Dynamic Fisher-weighted Model Merging via Bayesian Optimization","created":"2025-04-26","cited_by_count":12,"area":null},{"id":"2206.07996","title":"Continual Learning with Guarantees via Weight Interval Constraints","created":"2022-06-16","cited_by_count":11,"area":null},{"id":"2209.08660","title":"Learn the Time to Learn: Replay Scheduling in Continual Learning","created":"2022-09-18","cited_by_count":11,"area":null},{"id":"2502.14205","title":"Accurate Forgetting for Heterogeneous Federated Continual Learning","created":"2025-02-20","cited_by_count":11,"area":null},{"id":"2502.12706","title":"Scalable Model Merging with Progressive Layer-wise Distillation","created":"2025-02-18","cited_by_count":10,"area":null},{"id":"2306.07684","title":"Lookaround Optimizer: $k$ steps around, 1 step average","created":"2023-06-13","cited_by_count":9,"area":null},{"id":"2404.06391","title":"Exploring Neural Network Landscapes: Star-Shaped and Geodesic Connectivity","created":"2024-04-09","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":"2506.13234","title":"The Butterfly Effect: Neural Network Training Trajectories Are Highly Sensitive to Initial Conditions","created":"2025-06-16","cited_by_count":9,"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":"2502.01866","title":"Online Curvature-Aware Replay: Leveraging $\\mathbf{2^{nd}}$ Order Information for Online Continual Learning","created":"2025-02-03","cited_by_count":8,"area":null},{"id":"2509.21413","title":"Null-Space Filtering for Data-Free Continual Model Merging: Preserving Stability, Promoting Plasticity","created":"2025-09-25","cited_by_count":8,"area":null},{"id":"2109.11336","title":"Towards Generalized and Incremental Few-Shot Object Detection","created":"2021-09-23","cited_by_count":7,"area":null},{"id":"2404.05555","title":"On the Convergence of Continual Learning with Adaptive Methods","created":"2024-04-08","cited_by_count":7,"area":null},{"id":"2410.15143","title":"Budgeted Online Continual Learning by Adaptive Layer Freezing and Frequency-based Sampling","created":"2024-10-19","cited_by_count":7,"area":null},{"id":"2205.13359","title":"Feature Forgetting in Continual Representation Learning","created":"2022-05-26","cited_by_count":6,"area":null},{"id":"2210.14797","title":"Is Multi-Task Learning an Upper Bound for Continual Learning?","created":"2022-10-26","cited_by_count":6,"area":null},{"id":"2312.11973","title":"Continual Learning: Forget-free Winning Subnetworks for Video Representations","created":"2023-12-19","cited_by_count":6,"area":null},{"id":"2403.07968","title":"Do Deep Neural Network Solutions Form a Star Domain?","created":"2024-03-12","cited_by_count":6,"area":null},{"id":"2503.20110","title":"Efficient Model Development through Fine-tuning Transfer","created":"2025-03-25","cited_by_count":6,"area":null},{"id":"2506.16884","title":"The Importance of Being Lazy: Scaling Limits of Continual Learning","created":"2025-06-20","cited_by_count":6,"area":null},{"id":"2601.03641","title":"Agent-Dice: Disentangling Knowledge Updates via Geometric Consensus for Agent Continual Learning","created":"2026-01-07","cited_by_count":6,"area":"agents"},{"id":"2303.14962","title":"Forget-free Continual Learning with Soft-Winning SubNetworks","created":"2023-03-27","cited_by_count":5,"area":null},{"id":"2504.05342","title":"MASS: MoErging through Adaptive Subspace Selection","created":"2025-04-06","cited_by_count":5,"area":null},{"id":"2203.03692","title":"Low-Loss Subspace Compression for Clean Gains against Multi-Agent Backdoor Attacks","created":"2022-03-07","cited_by_count":4,"area":"safety"},{"id":"2209.08010","title":"Causes of Catastrophic Forgetting in Class-Incremental Semantic Segmentation","created":"2022-09-16","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":"2306.11305","title":"Progressive Fourier Neural Representation for Sequential Video Compilation","created":"2023-06-20","cited_by_count":4,"area":null},{"id":"2310.00113","title":"HyperMask: Adaptive Hypernetwork-based Masks for Continual Learning","created":"2023-09-29","cited_by_count":4,"area":null},{"id":"2410.01483","title":"Foldable SuperNets: Scalable Merging of Transformers with Different Initializations and Tasks","created":"2024-10-02","cited_by_count":4,"area":null},{"id":"2107.05445","title":"Disentangling Transfer and Interference in Multi-Domain Learning","created":"2021-07-02","cited_by_count":3,"area":null},{"id":"2204.04297","title":"Learning to Modulate Random Weights: Neuromodulation-inspired Neural Networks For Efficient Continual Learning","created":"2022-04-08","cited_by_count":3,"area":null},{"id":"2205.09891","title":"Interpolating Compressed Parameter Subspaces","created":"2022-05-19","cited_by_count":3,"area":null},{"id":"2312.04740","title":"Train 'n Trade: Foundations of Parameter Markets","created":"2023-12-07","cited_by_count":3,"area":null},{"id":"2403.03333","title":"Federated Learning over Connected Modes","created":"2024-03-05","cited_by_count":3,"area":null},{"id":"2406.05114","title":"The Expanding Scope of the Stability Gap: Unveiling its Presence in Joint Incremental Learning of Homogeneous Tasks","created":"2024-06-07","cited_by_count":3,"area":null},{"id":"2407.14738","title":"Flatness-aware Sequential Learning Generates Resilient Backdoors","created":"2024-07-20","cited_by_count":3,"area":"safety"},{"id":"2412.16469","title":"Chained Tuning Leads to Biased Forgetting","created":"2024-12-21","cited_by_count":3,"area":null},{"id":"2503.09271","title":"DitHub: A Modular Framework for Incremental Open-Vocabulary Object Detection","created":"2025-03-12","cited_by_count":3,"area":null},{"id":"2504.20033","title":"Mitigating Catastrophic Forgetting in the Incremental Learning of Medical Images","created":"2025-04-28","cited_by_count":3,"area":null},{"id":"2506.14951","title":"Flat Channels to Infinity in Neural Loss Landscapes","created":"2025-06-17","cited_by_count":3,"area":null},{"id":"2601.05580","title":"Generalizable and Adaptive Continual Learning Framework for AI-generated Image Detection","created":"2026-01-09","cited_by_count":3,"area":null},{"id":"2209.14996","title":"Multiple Modes for Continual Learning","created":"2022-09-29","cited_by_count":2,"area":null},{"id":"2305.14122","title":"Transferring Learning Trajectories of Neural Networks","created":"2023-05-23","cited_by_count":2,"area":null},{"id":"2309.15038","title":"HPCR: Holistic Proxy-based Contrastive Replay for Online Continual Learning","created":"2023-09-26","cited_by_count":2,"area":null},{"id":"2310.18639","title":"Towards Plastic and Stable Exemplar-Free Incremental Learning: A Dual-Learner Framework with Cumulative Parameter Averaging","created":"2023-10-28","cited_by_count":2,"area":null},{"id":"2407.20956","title":"An Effective Dynamic Gradient Calibration Method for Continual Learning","created":"2024-07-30","cited_by_count":2,"area":null},{"id":"2408.09838","title":"Mitigating the Stability-Plasticity Dilemma in Adaptive Train Scheduling with Curriculum-Driven Continual DQN Expansion","created":"2024-08-19","cited_by_count":2,"area":null},{"id":"2511.05171","title":"Model Merging Improves Zero-Shot Generalization in Bioacoustic Foundation Models","created":"2025-11-07","cited_by_count":2,"area":null}],"next_cursor":"100"}