{"list":"other","total":70,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"1611.07725","title":"iCaRL: Incremental Classifier and Representation Learning","created":"2016-11-23","cited_by_count":2333},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"1706.08840","title":"Gradient Episodic Memory for Continual Learning","created":"2017-06-26","cited_by_count":1898},{"id":"2006.16241","title":"The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization","created":"2020-06-29","cited_by_count":1850},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"1606.04671","title":"Progressive Neural Networks","created":"2016-06-15","cited_by_count":1361},{"id":"2001.06782","title":"Gradient Surgery for Multi-Task Learning","created":"2020-01-19","cited_by_count":1256},{"id":"1609.04747","title":"An overview of gradient descent optimization algorithms","created":"2016-09-15","cited_by_count":1033},{"id":"2112.08654","title":"Learning to Prompt for Continual Learning","created":"2021-12-16","cited_by_count":944},{"id":"2004.07211","title":"Dark Experience for General Continual Learning: a Strong, Simple Baseline","created":"2020-04-15","cited_by_count":911},{"id":"2111.07832","title":"iBOT: Image BERT Pre-Training with Online Tokenizer","created":"2021-11-15","cited_by_count":903},{"id":"1711.05769","title":"PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning","created":"2017-11-15","cited_by_count":898},{"id":"1905.13260","title":"Large Scale Incremental Learning","created":"2019-05-30","cited_by_count":732},{"id":"1708.01547","title":"Lifelong Learning with Dynamically Expandable Networks","created":"2017-08-04","cited_by_count":694},{"id":"1801.01423","title":"Overcoming catastrophic forgetting with hard attention to the task","created":"2018-01-04","cited_by_count":681},{"id":"2204.04799","title":"DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning","created":"2022-04-10","cited_by_count":642},{"id":"2211.13218","title":"CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learning","created":"2022-11-23","cited_by_count":450},{"id":"2103.09762","title":"Gradient Projection Memory for Continual Learning","created":"2021-03-17","cited_by_count":348},{"id":"2205.14865","title":"Prompt-aligned Gradient for Prompt Tuning","created":"2022-05-30","cited_by_count":341},{"id":"2002.01808","title":"K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters","created":"2020-02-05","cited_by_count":319},{"id":"2310.14152","title":"Orthogonal Subspace Learning for Language Model Continual Learning","created":"2023-10-22","cited_by_count":312},{"id":"1904.00310","title":"Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgetting","created":"2019-03-31","cited_by_count":302},{"id":"2111.11326","title":"DyTox: Transformers for Continual Learning with DYnamic TOken eXpansion","created":"2021-11-22","cited_by_count":291},{"id":"2307.06948","title":"Self-regulating Prompts: Foundational Model Adaptation without Forgetting","created":"2023-07-13","cited_by_count":272},{"id":"2207.12819","title":"S-Prompts Learning with Pre-trained Transformers: An Occam's Razor for Domain Incremental Learning","created":"2022-07-26","cited_by_count":246},{"id":"2106.14413","title":"Co$^2$L: Contrastive Continual Learning","created":"2021-06-28","cited_by_count":244},{"id":"2010.06808","title":"Just Pick a Sign: Optimizing Deep Multitask Models with Gradient Sign Dropout","created":"2020-10-14","cited_by_count":201},{"id":"2403.11549","title":"Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters","created":"2024-03-18","cited_by_count":199},{"id":"2404.00228","title":"InfLoRA: Interference-Free Low-Rank Adaptation for Continual Learning","created":"2024-03-30","cited_by_count":198},{"id":"2303.07338","title":"Revisiting Class-Incremental Learning with Pre-Trained Models: Generalizability and Adaptivity are All You Need","created":"2023-03-13","cited_by_count":184},{"id":"2401.16386","title":"Continual Learning with Pre-Trained Models: A Survey","created":"2024-01-29","cited_by_count":154},{"id":"2103.07113","title":"Training Networks in Null Space of Feature Covariance for Continual Learning","created":"2021-03-12","cited_by_count":143},{"id":"2003.09553","title":"Adversarial Continual Learning","created":"2020-03-21","cited_by_count":142},{"id":"2304.06027","title":"Continual Diffusion: Continual Customization of Text-to-Image Diffusion with C-LoRA","created":"2023-04-12","cited_by_count":141},{"id":"2310.07234","title":"Hierarchical Decomposition of Prompt-Based Continual Learning: Rethinking Obscured Sub-optimality","created":"2023-10-11","cited_by_count":121},{"id":"2403.12030","title":"Expandable Subspace Ensemble for Pre-Trained Model-Based Class-Incremental Learning","created":"2024-03-18","cited_by_count":117},{"id":"2303.06628","title":"Preventing Zero-Shot Transfer Degradation in Continual Learning of Vision-Language Models","created":"2023-03-12","cited_by_count":112},{"id":"2202.02931","title":"TRGP: Trust Region Gradient Projection for Continual Learning","created":"2022-02-07","cited_by_count":82},{"id":"2112.10017","title":"Continual Learning of a Mixed Sequence of Similar and Dissimilar Tasks","created":"2021-12-18","cited_by_count":81},{"id":"2305.19270","title":"Learning without Forgetting for Vision-Language Models","created":"2023-05-30","cited_by_count":79},{"id":"2204.02136","title":"Overcoming Catastrophic Forgetting in Incremental Object Detection via Elastic Response Distillation","created":"2022-04-05","cited_by_count":72},{"id":"2308.14960","title":"Read-only Prompt Optimization for Vision-Language Few-shot Learning","created":"2023-08-29","cited_by_count":58},{"id":"2011.12328","title":"Generalized Variational Continual Learning","created":"2020-11-24","cited_by_count":56},{"id":"2403.08568","title":"Consistent Prompting for Rehearsal-Free Continual Learning","created":"2024-03-13","cited_by_count":54},{"id":"2308.15827","title":"Introducing Language Guidance in Prompt-based Continual Learning","created":"2023-08-30","cited_by_count":49},{"id":"2304.05015","title":"Continual Semantic Segmentation with Automatic Memory Sample Selection","created":"2023-04-11","cited_by_count":39},{"id":"2207.07106","title":"Benchmarking Omni-Vision Representation through the Lens of Visual Realms","created":"2022-07-14","cited_by_count":38},{"id":"2401.10191","title":"Divide and not forget: Ensemble of selectively trained experts in Continual Learning","created":"2024-01-18","cited_by_count":38},{"id":"2208.12037","title":"Symbolic Replay: Scene Graph as Prompt for Continual Learning on VQA Task","created":"2022-08-24","cited_by_count":35},{"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},{"id":"2203.08404","title":"RBC: Rectifying the Biased Context in Continual Semantic Segmentation","created":"2022-03-16","cited_by_count":27},{"id":"2108.03613","title":"An EM Framework for Online Incremental Learning of Semantic Segmentation","created":"2021-08-08","cited_by_count":24},{"id":"2308.06217","title":"Continual Face Forgery Detection via Historical Distribution Preserving","created":"2023-08-11","cited_by_count":23},{"id":"2402.04129","title":"OVOR: OnePrompt with Virtual Outlier Regularization for Rehearsal-Free Class-Incremental Learning","created":"2024-02-06","cited_by_count":20},{"id":"2407.05229","title":"HiDe-PET: Continual Learning via Hierarchical Decomposition of Parameter-Efficient Tuning","created":"2024-07-07","cited_by_count":20},{"id":"2106.15827","title":"When Video Classification Meets Incremental Classes","created":"2021-06-30","cited_by_count":18},{"id":"2112.07241","title":"Static-Dynamic Co-Teaching for Class-Incremental 3D Object Detection","created":"2021-12-14","cited_by_count":16},{"id":"2403.10245","title":"CoLeCLIP: Open-Domain Continual Learning via Joint Task Prompt and Vocabulary Learning","created":"2024-03-15","cited_by_count":15},{"id":"2210.04513","title":"Improving Continual Relation Extraction through Prototypical Contrastive Learning","created":"2022-10-10","cited_by_count":14},{"id":"2402.16189","title":"One-stage Prompt-based Continual Learning","created":"2024-02-25","cited_by_count":14},{"id":"2311.14905","title":"Class Gradient Projection For Continual Learning","created":"2023-11-25","cited_by_count":11},{"id":"2311.15414","title":"KOPPA: Improving Prompt-based Continual Learning with Key-Query Orthogonal Projection and Prototype-based One-Versus-All","created":"2023-11-26","cited_by_count":6},{"id":"2212.09097","title":"Continual Knowledge Distillation for Neural Machine Translation","created":"2022-12-18","cited_by_count":4}],"next_cursor":null}