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

304 papers34 papers in the last four weeks, up 31% on the four weeks before. 0.2% of all new papers.

Reasoning Portability: Guiding Continual Learning for MLLMs in the RLVR Era
May 17, 2026Qiuhe Hong, Yuyang Liu, Shuo Yang +3KL-Regularized RL Continual Learning
1Shenzhen Graduate School of Peking University · Centre for Artificial Intelligence and Robotics, HKISI, CAS · 3Peng Cheng Laboratory
Expandable, Compressible, Mineable: Open-World Thermal Image Restoration
May 16, 2026Pu Li, Huafeng Li, Yafei Zhang +3Continual Learning All-in-One Image Restoration
Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Yunnan, China · School of Mathematics and Statistics, Yunnan University, Yunnan, China · Shenzhen Key Laboratory of Visual Object Detection and Recognition, Harbin Institute of Technology, Shenzhen, China
Shapley Neuron Values for Continual Learning: Which Neurons Matter Most?
May 15, 2026Mohammad Ali Vahedifar, Abhisek Ray, Qi ZhangTask-Incremental Learning Class-Incremental Learning
DIGIT and Department of Electrical and Computer Engineering, Aarhus University, Denmark
ACE-LoRA: Adaptive Orthogonal Decoupling for Continual Image Editing
May 14, 2026Yuehao Liu, Weijia Zhang, Xuanming Shang +4Continual Learning Diffusion Model Fine-Tuning
Shanghai Jiao Tong University · Nanjing University · VIVO
CogniFold: Always-On Proactive Memory via Cognitive Folding
May 13, 2026Suli Wang, Yiqun Duan, Yu Deng +5Cognitive Architectures for AI Agents Continual Learning
1OpenNorve · University of Cambridge · 3NVIDIA +1
Scaling few-shot spoken word classification with generative meta-continual learning
May 13, 2026Louise Beyers, Batsirayi Mupamhi Ziki, Ruan van der MerweFew-Shot Audio Classification Continual Learning
Bytefuse
DRIFT: A Benchmark for Task-Free Continual Graph Learning with Continuous Distribution Shifts
May 13, 2026Guiquan Sun, Xikun Zhang, Jingchao Ni +1Distribution Shift Continual Learning
University of Connecticut · RMIT University · University of Houston
FuTCR: Future-Targeted Contrast and Repulsion for Continual Panoptic Segmentation
May 12, 2026Nicholas Ikechukwu, Keanu Nichols, Deepti Ghadiyaram +1Contrastive Learning Image Segmentation
Boston University
KAN-CL: Per-Knot Importance Regularization for Continual Learning with Kolmogorov-Arnold Networks
May 12, 2026Minjong CheonRegularization-Based Continual Learning Continual Learning
Sejong University Department of Computer Science and Engineering
More Edits, More Stable: Understanding the Lifelong Normalization in Sequential Model Editing
May 12, 2026Xin Ma, Wei Chen, Qi Liu +4Knowledge Editing Continual Learning
State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Anhui, China.
Online Continual Learning with Dynamic Label Hierarchies
May 12, 2026Xinrui Wang, Shao-Yuan Li, Bartłomiej Twardowski +2Class-Incremental Learning Hierarchical Classification
College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics · MIIT Key Laboratory of Pattern Analysis and Machine Intelligence · Computer Vision Center, Spain +4
MIST: Reliable Streaming Decision Trees for Online Class-Incremental Learning via McDiarmid Bound
May 12, 2026Phu-Hoa Pham, Chi-Nguyen Tran, Nguyen Lam Phu Quy +3Class-Incremental Learning Continual Learning
Faculty of Information and Technology University of Science Vietnam National University Ho Chi Minh City, Vietnam · Department of Computer Science University of Warwick Coventry, United Kingdom
Why Zeroth-Order Adaptation May Forget Less: A Randomized Shaping Theory
May 11, 2026Yao Shu, Jian Mu, Zhongxiang DaiZeroth-Order Optimization Continual Learning
HKUST(GZ)
Towards Understanding Continual Factual Knowledge Acquisition of Language Models: From Theory to Algorithm
May 11, 2026Haoyu Wang, Yifan Shang, Zhongxiang Sun +3Continual Learning for LLMs Generative Replay
Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China · School of Artificial Intelligence and Data Science, University of International Business and Economics, Beijing, China
CMKL: Modality-Aware Continual Learning for Evolving Biomedical Knowledge Graphs
May 11, 2026Yousef A. Radwan, Yao Li, Qing Qing +5Continual Learning KG Embedding
Technology, Innovation, Entrepreneurship Department King Abdullah University of Science and Technology · School of Computing and Information Systems The University of Melbourne · College of Computer Science and Technology Jilin University +2
Joint sparse coding and temporal dynamics support context reconfiguration
May 11, 2026Qianqian Shi, Yue Che, Faqiang Liu +6Representation Learning Continual Learning
Center for Brain-Inspired Computing Research (CBICR), Department of Precision Instrument, Tsinghua University, Beijing, China · Guangdong Institute of Intelligence Science and Technology, Hengqin, China · Optical Memory National Engineering Research Center, Tsinghua University, Beijing, China +3
Lost or Hidden? A Concept-Level Forgetting in Supervised Continual Learning
May 10, 2026Katarzyna Filus, Kamil Faber, Roberto Corizzo +1Visual Representation Learning Continual Learning
Institute of Theoretical and Applied Informatics Polish Academy of Sciences, Gliwice, Poland · AGH University of Krakow Krakow, Poland · American University Washington DC, USA +1
Predicting Plasticity in Deep Continual Learning: A Theoretical Perspective
May 9, 2026Jiuqi Wang, Jayanth Srinivasa, Claire Chen +3Deep Learning Optimization Loss of Plasticity
University of Virginia · Cisco Research · California Institute of Technology +1
Cross-Sample Relational Fusion: Unifying Domain Generalization and Class-Incremental Learning
May 9, 2026Zhen-Hao Xie, Yan Wang, Hao Sun +3Class-Incremental Learning Continual Learning
School of Artificial Intelligence and the State Key Laboratory of Novel Software Technology, Nanjing University, Nanjing, China
Characterizing and Correcting Effective Target Shift in Online Learning
May 8, 2026Ziyan Li, Naoki HirataniLabel Shift Kernel Regression
Department of Physics Washington University in St. Louis St. Louis, USA · Department of Neuroscience Washington University in St. Louis St. Louis, USA
Revitalizing the Beginning: Avoiding Storage Dependency for Model Merging in Continual Learning
May 8, 2026Xi Wang, Cheng DengStorage-Efficient Continual Learning Continual Learning
School of Electronic Engineering, Xidian University, Xi’an, Shaanxi, China.
Hierarchical Dual-Subspace Decoupling for Continual Learning in Vision-Language Models
May 8, 2026Mengxin Qin, Xiang Zhang, Kun Wei +2Class-Incremental Learning Vision-Language Models
School of Electronic Engineering, Xidian University Xi’an 710071, China
Attribution-Based Neuron Utility for Plasticity Restoration in Deep Networks
May 7, 2026Patrick Elisii, Lucas Beauchemin, Dawer JamshedGradient-Based Attribution Loss of Plasticity
The Vanguard Group, Inc.
GeoStack: A Framework for Quasi-Abelian Knowledge Composition in VLMs
May 7, 2026Pranav Mantini, Shishir K. ShahVision-Language Models VLM Adaptation
Department of Computer Science University of Houston · The University of Oklahoma School of Computer Science
Scene-Adaptive Continual Learning for CSI-based Human Activity Recognition with Mixture of Experts
May 7, 2026Wenhan Zheng, Yuyi Mao, Ivan Wang-Hei HoAdaptive Inference Human Activity Recognition
Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong · School of Computer Science and Engineering, The Macau University of Science and Technology, Macau
Shortcut Solutions Learned by Transformers Impair Continual Compositional Reasoning
May 6, 2026William T. Redman, Erik C. Johnson, Brian RobinsonCompositional Reasoning Continual Learning
Johns Hopkins Applied Physics Lab
Prompt-Anchored Vision-Text Distillation for Lifelong Person Re-identification
May 6, 2026Wen Wen, Hao Chen, Shiliang ZhangCross-Modal Knowledge Distillation Continual Learning
University of Electronic Science and Technology of China, China · Harbin Institute of Technology, Shenzhen, China · Peking University, China
Towards Open World Sound Event Detection
May 5, 2026P. H. Hai, L. T. Minh, L. H. SonContinual Learning Detection Transformer
VNU University of Engineering and Technology, Hanoi, 100000, Vietnam · Artificial Intelligence Research Center, VNU Information Technology Institute, Hanoi, 100000, Vietnam
Adaptive Data Compression and Reconstruction for Memory-Bounded EEG Continual Learning
May 4, 2026Chengcheng XieElectroencephalography Continual Learning
Beihang University
MPCS: Neuroplastic Continual Learning via Multi-Component Plasticity and Topology-Aware EWC
May 4, 2026Joern HentschStability-Plasticity Dilemma Dynamic Neural Networks

May 17, 2026J/K move · Enter open · S save

Reasoning Portability: Guiding Continual Learning for MLLMs in the RLVR Era

Qiuhe Hong, Yuyang Liu, Shuo Yang, Tiantian Peng+2

1Shenzhen Graduate School of Peking University · Centre for Artificial Intelligence and Robotics, HKISI, CAS · 3Peng Cheng Laboratory

KL-Regularized RL Continual Learning Continual Learning for VLMs

Open paper AskPDF arXiv

Vision-Language Models in Continual Learning (VLM-CL) aim to continuously adapt to new multimodal tasks while retaining prior knowledge. The emerging paradigm that couples Multimodal Large Language Models (MLLMs) with Reinforcement Learning with Verifiable Rewards (RLVR) calls for a new pattern to guide continual adaptation. Advances in reasoning capability now make it feasible to impose constraints at the reasoning level. We formalize portability, a sample-level measure of how reusable the previous policy's behavior is on a new task, and empirically show that reasoning-level signals remain reliable on out-of-distribution samples while answer-level signals do not. We instantiate this as Reasoning Portability (RP) and propose Reasoning-based Dynamic Balance Continual Learning (RDB-CL), which modulates the per-sample Kullback-Leibler regularization in RLVR according to RP: a tight anchor preserves reusable reasoning on high-RP samples, while a relaxed anchor on low-RP samples permits exploration of new reasoning pathways. Experiments show that RDB-CL consistently outperforms baselines, improving Last accuracy by +12.0% over the vanilla RLVR baseline.