Continual Learning

Follow this topic Ask about this topic

Continual Learning studies how models adapt to sequences of tasks or non-stationary data without losing useful earlier knowledge, a challenge known as catastrophic forgetting. Common approaches replay selected examples, regularize updates to protect important parameters, isolate tasks with adapters or separate subnetworks, or manage knowledge through prompts, memory, and model expansion. Methods are tested on class- and domain-incremental image benchmarks such as CIFAR and ImageNet, as well as task-free streams and applications in language, robotics, and healthcare. A central tension is balancing retention with the capacity to learn, while evaluations increasingly question assumptions such as known task boundaries and seek to measure transfer, recovery, resource use, and performance under realistic shifts.

Latest papers

305 papers36 papers in the last four weeks, up 89% on the four weeks before. 0.2% of all new papers.

Catastrophic Forgetting as Accessibility Collapse: A Three-Level Framework for Knowledge Persistence in Continual Learning
Jun 4, 2026Ayushman Trivedi, Bhavika MelwaniContinual Learning Catastrophic Forgetting
Independent Researchers
Continual Learning Bench: Evaluating Frontier AI Systems in Real-World Stateful Environments
Jun 4, 2026Parth Asawa, Christopher M. Glaze, Gabriel Orlanski +7Continual Learning for LLM Agents Continual Learning for LLMs
UC Berkeley · Snorkel AI · University of Wisconsin-Madison +1
CLaaS: Continual learning as a service for sample efficient online learning
Jun 4, 2026Kion Fallah, Silen Naihin, Barak Widawsky +1Continual Learning for LLM Agents Continual Learning
1Resolute Labs · 2South Park Commons · 3Incept Labs
Rethinking Continual Experience Internalization for Self-Evolving LLM Agents
Jun 3, 2026Jingwen Chen, Wenkai Yang, Shengda Fan +7Continual Learning for LLM Agents Continual Learning for LLMs
1Gaoling School of Artificial Intelligence, Renmin University of China · School of Software, Beihang University · 3Meituan
Re-Evaluating Continual Learning with Few-Shot Adaptation
Jun 2, 2026Amogh Inamdar, Matthew So, Vici Milenia +1Continual Learning
Department of Computer Science Columbia University
SkillHarness: Harnessing Safe Skills for Computer-Use Agents
Jun 2, 2026Yurun Chen, Biao Yi, Keting Yin +1Computer-Use Agents Continual Learning
Zhejiang University
Forgetting is Not Erasure: Recovering Latent Knowledge via Transport Keys
Jun 1, 2026Archie ChaudhuryContinual Learning Representation Alignment
Axionic Labs
G2LoRA: Gradient Orthogonal Low-Rank Adaptation Framework for Graph Continual Learning on Text-Attributed Graphs
Jun 1, 2026Yuhan Wang, Yibo Ding, Yutong Ye +4Continual Learning Low-Rank Adaptation
School of Computer Science and Engineering, Beihang University Beijing, China · Department of Statistics, Columbia University New York, NY, USA · College of Computer Science, Beijing University of Technology Beijing, China
Continual Learning as a Multiphase Moving-Boundary Problem
Jun 1, 2026Snigdha Chandan KhilarContinual Learning Catastrophic Forgetting
Independent Researcher
EvoBrain: Continual Learning of EEG Foundation Models Across Heterogeneous BCI Tasks
Jun 1, 2026Yangxuan Zhou, Sha Zhao, Jiquan Wang +2Brain-Computer Interfaces EEG Decoding
State Key Laboratory of Brain-machine Intelligence and College of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang, China · MOE Frontier Science Center for Brain Science and Brain-Machine Integration, Zhejiang University, Hangzhou, Zhejiang, China
Task diversity produces systematic transfer but inhibits continual reinforcement learning
May 30, 2026Purab Seth, Neil Shah, Ishaan Sinha +4Transfer Learning Reinforcement Learning
Harvard College · University of Washington · Kempner Institute for the Study of Natural and Artificial Intelligence, Harvard University +1
SHARP: Sleep-based Hierarchical Accelerated Replay for Long Range Non-Stationary Temporal Pattern Recognition
May 30, 2026Jayanta Dey, Shikhar Srivastava, Itamar Lerner +2Memory-Augmented Neural Networks Continual Learning
University of Texas at San Antonio, USA · University of Rochester, USA
Regime-Adaptive Continual Learning for Portfolio Management
May 29, 2026Chaofan Pan, Lingfei Ren, Linbo Xiong +3Continual Learning Portfolio Optimization
Southwestern University of Finance and Economics · Shanxi University
Active Continual Learning with Metaplastic Binary Bayesian Neural Networks
May 28, 2026Kellian Cottart, Théo Ballet, Djohan Bonnet +1Bayesian Neural Networks Binary Neural Networks
Université Paris-Saclay, CNRS, Centre de Nanosciences et de Nanotechnologies, Palaiseau, France · Forschungszentrum Jülich, Germany
TIMEGATE: Sustainable Time-Boxed Promotion Gates for Continual ML Adaptation Under Resource Constraints
May 27, 2026Abhijit Chakraborty, Suddhasvatta Das, Yash Shah +2Energy-Efficient ML Continual Learning
School of Computing and Augmented Intelligence, Arizona State University, Tempe, USA
Janus-LoRA: A Balanced Low-Rank Adaptation for Continual Learning
May 27, 2026Cheng Chen, Pengpeng Zeng, Yuyu Guo +3Stability-Plasticity Dilemma Continual Learning
School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China · School of Computer Science and Technology, Tongji University, Shanghai, China · Independent Researcher +1
Self-Supervised Online Robot-Agnostic Traversability Estimation for Open-World Environments
May 27, 2026Julia Hindel, Simon Bultmann, Houman Masnavi +2Continual Robot Learning Robot Traversability Estimation
Department of Computer Science, University of Freiburg, Germany.
CLANE: Continual Learning of Actions on Neuromorphic Hardware from Event Cameras
May 27, 2026Elvin Hajizada, Michael Neumeier, Edward Paxon Frady +4Event-Based Vision Continual Learning
Institute of Informatics, University of Munich (LMU), Munich, Germany · fortiss GmbH, Neuromorphic Computing, Munich, Germany · Technical University of Munich, TUM School of CIT, Munich, Germany +5
COVD: Continual Open-Vocabulary Object Detection with Novel Concept Injection
May 26, 2026Yupeng Zhang, Ruize Han, Yuzhong Feng +3Open-Vocabulary Object Detection VLM Adaptation
Tianjin University. · Shenzhen University of Advanced Technology.
Energy-Structured Low-Rank Adaptation for Continual Learning
May 26, 2026Longhua Li, Lei Qi, Qi Tian +1Continual Learning Low-Rank Adaptation
School of Computer Science and Engineering, Southeast University, Nanjing, China · Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, China · Huawei Technologies, Shenzhen, China
Architecture-driven Shift: towards a lightweight selector for capturing the trends of logit shift
May 26, 2026Zhong Ye, Yu Hu, Ruilin TangContinual Learning Neural Network Training Dynamics
School of Computer Science and Technology Guangdong University of Technology Guangzhou, China · School of Computer Science and Engineering2026 South China University of Technology Guangzhou, China
Grow-Prune-Freeze Networks: Adaptive & Continual Learning Technique for Olfactory Navigation
May 24, 2026Kordel K. France, Ovidiu DaescuNon-Stationary RL Partially Observable RL
Department of Computer Science, University of Texas at Dallas, USA
SEED: Semi-supervised Continual MalwarE Detection for Tackling ConcEpt Drift on a BuDget
May 24, 2026Suresh Kumar Amalapuram, Bikraj Shresta, Siva Ram murthy Chebiyam +2Concept Drift Continual Learning
Indian Institute of Technology Ropar, India · Indian Institute of Technology Hyderabad, India
Rethinking Continual Learning for Speech and Audio: A Representation-Centric Taxonomy and Open Problems
May 24, 2026Yang Xiao, Siyi Wang, Eun-Jung Holden +1Audio Representation Learning Speech Foundation Models
University of Melbourne, Melbourne, Australia.
Temporal Concept Drift in Legal Judgment Prediction: Neural Baselines Across Three Epochs of Ukrainian Court Decisions
May 23, 2026Volodymyr OvcharovLanguage Model Pretraining Legal NLP
Tunable MAGMAX: Preference-Aware Model Merging for Continual Learning
May 20, 2026Kei Hiroshima, Kento Uchida, Shinichi ShirakawaContinual Learning Language Model Merging
Yokohama National University, Yokohama Kanagawa 240-8501, Japan
Auto-Dreamer: Learning Offline Memory Consolidation for Language Agents
May 20, 2026Chongrui Ye, Yuxiang Liu, Yu Wang +5Continual Learning for LLM Agents Continual Learning
University of Illinois Urbana-Champaign · University of California San Diego
Continual Segmentation under Joint Nonstationarity
May 19, 2026Prashant Pandey, Himanshu Kumar, Devineni Sri Venkatraya Chowdary +1Class-Incremental Learning Continual Learning
Bharti School of Telecommunications Technology & Management, Indian Institute of Technology, Delhi, India · Yardi School of Artificial Intelligence, Indian Institute of Technology, Delhi, India · Department of Computer Science and Engineering, Indian Institute of Technology (Indian School of Mines), Dhanbad, India
On-Device Continual Learning with Dual-Stage Buffer and Dynamic Loss for Point-of-Care Pneumonia Diagnosis
May 19, 2026Danu KimMedical Diagnosis Continual Learning
Korea International School, Jeju Campus, Jeju-do 63644, Republic of Korea
PMF-CL: Pareto-Minimal-Forgetting Continual Learner for Conflicting Tasks
May 18, 2026Srijith Nair, Atilla Eryilmaz, Jia LiuContinual Learning Catastrophic Forgetting
Department of Electrical and Computer Engineering The Ohio State University Columbus, OH 43201

Jun 4, 2026J/K move · Enter open · S save

Catastrophic Forgetting as Accessibility Collapse: A Three-Level Framework for Knowledge Persistence in Continual Learning

Ayushman Trivedi, Bhavika Melwani

Independent Researchers

Continual Learning Catastrophic Forgetting

Open paper AskPDF arXiv

Catastrophic forgetting is commonly interpreted as the irreversible erasure of previously acquired knowledge during sequential learning. In this work, we investigate an alternative perspective: that forgetting may arise not from complete destruction of task representations but from a loss of accessibility to preserved information. We introduce a three-level framework separating knowledge storage, representation, and accessibility, and evaluate each component through a series of continual-learning experiments on sequential CIFAR-100 classification using ResNet-18. Our analysis combines checkpoint persistence, linear probing, representation geometry, classifier-reset recovery, and layer-wise recoverability experiments. We observe complete behavioral forgetting of earlier tasks, with task accuracy collapsing from 54.8% to 0%, while linear probe performance retains approximately 76% of the original representational information. Furthermore, retraining only the final classifier restores 75.7% of the original task performance without modifying the backbone network. Layer-wise analysis reveals that early and intermediate layers preserve highly recoverable task information despite severe degradation at later stages. Projection-energy and principal-angle analyses indicate that retained knowledge persists as distributed high-dimensional representations rather than through preservation of a small dominant subspace. These findings suggest that catastrophic forgetting is better characterized as an accessibility failure than complete representational erasure, and that substantial task-relevant information remains embedded within neural representations even after functional forgetting has occurred.