Continual Learning

Follow this field Ask about this field

Recent momentum

emerging

0 papers in the last 28 days · 0.0% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this field, kept on the site without email delivery.

Period ending 2026-09-21

14 new papers

A weekly snapshot of new work published in Continual Learning.

Period ending 2026-09-14

11 new papers

A weekly snapshot of new work published in Continual Learning.

Period ending 2026-09-07

8 new papers

A weekly snapshot of new work published in Continual Learning.

Inside this field

Focused directions

Focused topic

Continual Learning Methods

Within Continual Learning

229 papersExplore

Focused topic

Efficient Continual Learning

Within Continual Learning

195 papersExplore

Focused topic

Catastrophic Forgetting

Within Continual Learning

151 papersExplore

Focused topic

Forgetting

Within Continual Learning

105 papersExplore

Focused topic

Plasticity

Within Continual Learning

81 papersExplore

Focused topic

Domain Incremental Learning

Within Continual Learning

62 papersExplore

Focused topic

Retention

Within Continual Learning

51 papersExplore

621 papers

Latest in Continual Learning

Browse all topics →

Unlocking Patch-Level Features for CLIP-Based Class-Incremental Learning
May 13, 2026Hao Sun, Zi-Jun Ding, Da-Wei ZhouDomain Incremental Learning Spatial Patching
KIT-TIP-NLP at MultiPride: Continual Learning with Multilingual Foundation Model
May 13, 2026Barathi Ganesh HB, Michal Ptaszynski, Rene Melendez +1Multilingual Language Models Hate Speech
Continual Fine-Tuning of Large Language Models via Program Memory
May 13, 2026Hung Le, Svetha VenkateshEfficient Continual Learning Continual Fine-Tuning
DRIFT: A Benchmark for Task-Free Continual Graph Learning with Continuous Distribution Shifts
May 13, 2026Guiquan Sun, Xikun Zhang, Jingchao Ni +1Efficient Continual Learning Graph Representation Learning
Safe Continual Reinforcement Learning under Nonstationarity via Adaptive Safety Constraints
May 13, 2026Timofey TomashevskiySafety Constraints Deep Reinforcement Learning
Always Learning, Always Mixing: Efficient and Simple Data Mixing All The Time
May 13, 2026Michael Y. Hu, Apurva Gandhi, Kyunghyun Cho +2Continual Learning Methods On-Policy Distillation
Lifelong Learning in Vision-Language Models: Enhanced EWC with Cross-Modal Knowledge Retention
May 12, 2026Hamza Ahmed Durrani, Rafay Suleman DurraniLarge Vision Language Models Cross-Modal Alignment
Low-Rank Adapters Initialization via Gradient Surgery for Continual Learning
May 12, 2026Joana Pasquali, Ramiro N. Barros, Arthur S. Bianchessi +7Low-Rank Adaptation Adapters Efficient Continual Learning
Learning with Rare Success but Rich Feedback via Reflection-Enhanced Self-Distillation
May 12, 2026Yuwei Zhang, Sha Li, Changlong Yu +9Unsupervised On-Policy Self-Distillation Reinforcement Learning Post-Training
Early Data Exposure Improves Robustness to Subsequent Fine-Tuning
May 12, 2026Lawrence Feng, Gaurav R. Ghosal, Jacob Mitchell Springer +2Continual Fine-Tuning Trainability
Learning, Fast and Slow: Towards LLMs That Adapt Continually
May 12, 2026Rishabh Tiwari, Kusha Sareen, Lakshya A Agrawal +6In-Context Learning Catastrophic Forgetting
ORBIT: Preserving Foundational Language Capabilities in GenRetrieval via Origin-Regulated Merging
May 12, 2026Neha Verma, Nikhil Mehta, Shao-Chuan Wang +7Large Language Model Fine-Tuning Catastrophic Forgetting
KAN-CL: Per-Knot Importance Regularization for Continual Learning with Kolmogorov-Arnold Networks
May 12, 2026Minjong CheonCatastrophic Forgetting Kolmogorov-Arnold Networks
Intrinsic Vicarious Conditioning for Deep Reinforcement Learning
May 12, 2026Rodney A Sanchez, Ferat Sahin, Alex Ororbia +1Deep Reinforcement Learning Continual Learning Methods
Beyond Point-wise Neural Collapse: A Topology-Aware Hierarchical Classifier for Class-Incremental Learning
May 12, 2026Huiyu Yi, Zhiming Xu, Dunwei Tu +3Domain Incremental Learning Neural Collapse
More Edits, More Stable: Understanding the Lifelong Normalization in Sequential Model Editing
May 12, 2026Xin Ma, Wei Chen, Qi Liu +4Multimodal Knowledge Editing Catastrophic Forgetting
Stop Marginalizing My Dreams: Model Inversion via Laplace Kernel for Continual Learning
May 12, 2026Patryk Krukowski, Jacek Tabor, Przemysław Spurek +2Efficient Continual Learning Continual Learning Methods
Online Continual Learning with Dynamic Label Hierarchies
May 12, 2026Xinrui Wang, Shao-Yuan Li, Bartłomiej Twardowski +2Efficient Continual Learning Continual Learning Methods
Unlocking Compositional Generalization in Continual Few-Shot Learning
May 12, 2026Phu-Quy Nguyen-Lam, Phu-Hoa Pham, Dao Sy Duy Minh +3Few-Shot Learning Self-Supervised Vision Transformers
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 +3Efficient Continual Learning Decision Trees
SplitFed-CL: A Split Federated Co-Learning Framework for Medical Image Segmentation with Inaccurate Labels
May 11, 2026Zahra Hafezi Kafshgari, Hadi Hadizadeh, Parvaneh SaeediMedical Image Segmentation Federated Learning
Dynamic Cross-Modal Prompt Generation for Multimodal Continual Instruction Tuning
May 11, 2026Tao Hu, Da-Wei ZhouMultimodal Instruction Tuning Instruction Tuning
Why Zeroth-Order Adaptation May Forget Less: A Randomized Shaping Theory
May 11, 2026Yao Shu, Jian Mu, Zhongxiang DaiZeroth-Order Optimization Catastrophic Forgetting
PrimeKG-CL: A Continual Graph Learning Benchmark on Evolving Biomedical Knowledge Graphs
May 11, 2026Yousef A. Radwan, Yao Li, Qing Qing +5Biomedical Knowledge Graph Graph Representation Learning
CMKL: Modality-Aware Continual Learning for Evolving Biomedical Knowledge Graphs
May 11, 2026Yousef A. Radwan, Yao Li, Qing Qing +5Knowledge Graph Embeddings Biomedical Knowledge Graph
Joint sparse coding and temporal dynamics support context reconfiguration
May 11, 2026Qianqian Shi, Yue Che, Faqiang Liu +6Catastrophic Forgetting Dense Associative Memory
UFO: A Unified Flow-Oriented Framework for Robust Continual Graph Learning
May 11, 2026Danhui Zhang, Zhe Wang, Qing Qing +6Graph Representation Learning Efficient Continual Learning
Trajectory Supervision for Continual Tool-Use Learning in LLMs
May 10, 2026Vishnu Vardhan Reddy, Sagnik Chatterjee, Soumik BhattaContinual Learning Methods Training Data
Lost or Hidden? A Concept-Level Forgetting in Supervised Continual Learning
May 10, 2026Katarzyna Filus, Kamil Faber, Roberto Corizzo +1Catastrophic Forgetting Continual Learning Methods
FreeMOCA: Memory-Free Continual Learning for Malicious Code Analysis
May 10, 2026Zahra Asadi, Haeseung Jeon, Sohyun Han +3Malware Detection Efficient Continual Learning
Overcoming Catastrophic Forgetting in Visual Continual Learning with Reinforcement Fine-Tuning
May 10, 2026Meng Lou, Hanzhong Guo, Linwei Chen +1Catastrophic Forgetting Reinforcement Fine-Tuning
Reflection Anchors for Propagation-Aware Visual Retention in Long-Chain Multimodal Reasoning
May 10, 2026Xuan Gong, Hanbo Huang, Hao Zheng +4Multimodal Reasoning Residual Anchoring
Geometry Conflict: Explaining and Controlling Forgetting in LLM Continual Post-Training
May 10, 2026Yuanyi Wang, Yifan Yang, Su Lu +9Catastrophic Forgetting Large Language Model Post-Training
NEXUS: Continual Learning of Symbolic Constraints for Safe and Robust Embodied Planning
May 10, 2026Tiehan Cui, Peipei Liu, Yanxu Mao +3Embodied Agents Classical Planning
The Geometry of Forgetting: Temporal Knowledge Drift as an Independent Axis in LLM Representations
May 9, 2026Rania Elbadry, Ahmed Heakl, Fan Zhang +4Forgetting Gradient Staleness
Predicting Plasticity in Deep Continual Learning: A Theoretical Perspective
May 9, 2026Jiuqi Wang, Jayanth Srinivasa, Claire Chen +3Plasticity Efficient Continual Learning
Muon-OGD: Muon-based Spectral Orthogonal Gradient Projection for LLM Continual Learning
May 9, 2026Binghang Lu, Zheyuan Deng, Runyu Zhang +6Muon Optimizer Efficient Continual Learning
Cross-Sample Relational Fusion: Unifying Domain Generalization and Class-Incremental Learning
May 9, 2026Zhen-Hao Xie, Yan Wang, Hao Sun +3Domain Incremental Learning Cross-Task Knowledge Transfer
Unlearners Can Lie: Evaluating and Improving Honesty in LLM Unlearning
May 9, 2026Renjie Gu, Jiazhen Du, Yihua Zhang +1Large Language Model Unlearning Large Language Model Reliability
Continuity Laws for Sequential Models
May 8, 2026Annan Yu, Dongwei Lyu, N. Benjamin ErichsonSequence Modeling Efficient Continual Learning
Political Plasticity: An Analysis of Ideological Adaptability in Large Language Models
May 8, 2026Bruno Bianchi, Diego Tiscornia, Matias Travizano +1Large Language Model Bias Ideology
Characterizing and Correcting Effective Target Shift in Online Learning
May 8, 2026Ziyan Li, Naoki HirataniLearning-Augmented Algorithms Online Learning
Revitalizing the Beginning: Avoiding Storage Dependency for Model Merging in Continual Learning
May 8, 2026Xi Wang, Cheng DengEfficient Continual Learning Continual Model Merging
Hierarchical Dual-Subspace Decoupling for Continual Learning in Vision-Language Models
May 8, 2026Mengxin Qin, Xiang Zhang, Kun Wei +2Continual Learning Methods Vision-Language Model Adaptation
DIMoE-Adapters: Dynamic Expert Evolution for Continual Learning in Vision-Language Models
May 8, 2026Mengxin Qin, Xiang Zhang, Xi Wang +3Vision-Language Model Adaptation Continual Learning Methods
SR $^2$ -LoRA: Self-Rectifying Inter-layer Relations in Low-Rank Adaptation for Class-Incremental Learning
May 8, 2026Fengqiang Wan, Yipeng Lin, Kan Lv +1Domain Incremental Learning Catastrophic Forgetting
StrLoRA: Towards Streaming Continual Visual Instruction Tuning for MLLMs
May 8, 2026Chang Che, Ziqi Wang, Hui Ma +2Multimodal Instruction Tuning Efficient Continual Learning
Limits of Reliability and Scaling in Language Models
May 8, 2026Subhabrata MajumdarNeural Scaling Laws Trade-Off
Attribution-Based Neuron Utility for Plasticity Restoration in Deep Networks
May 7, 2026Patrick Elisii, Lucas Beauchemin, Dawer JamshedEfficient Continual Learning Plasticity
Optimizer-Model Consistency: Full Finetuning with the Same Optimizer as Pretraining Forgets Less
May 7, 2026Yuxing Liu, Jianyu Wang, Tong ZhangSupervised Fine-Tuning Model Pretraining
On the Implicit Reward Overfitting and the Low-rank Dynamics in RLVR
May 7, 2026Hao Ye, Jisheng Dang, Junfeng Fang +7Reinforcement Learning With Verifiable Reward Reinforcement Learning Post-Training
GeoStack: A Framework for Quasi-Abelian Knowledge Composition in VLMs
May 7, 2026Pranav Mantini, Shishir K. ShahCatastrophic Forgetting
Scene-Adaptive Continual Learning for CSI-based Human Activity Recognition with Mixture of Experts
May 7, 2026Wenhan Zheng, Yuyi Mao, Ivan Wang-Hei HoHuman Activity Recognition Cross-Sensor Generalization
When Does Trimming Help Conformal Prediction? A Retained-Law Diagnostic under Calibration Contamination
May 7, 2026Congye WangContamination Conformal Prediction
Beyond Forgetting in Continual Medical Image Segmentation: A Comprehensive Benchmark Study
May 7, 2026Bomin Wang, Hangqi Zhou, Yibo Gao +1Medical Image Segmentation Efficient Continual Learning
Navigating by Old Maps: The Pitfalls of Static Mechanistic Localization in LLM Post-Training
May 7, 2026Hang Chen, Jiaying Zhu, Hongyang Chen +3Large Language Model Post-Training Catastrophic Forgetting
ICU-Bench:Benchmarking Continual Unlearning in Multimodal Large Language Models
May 7, 2026Yuhang Wang, Wenjie Mei, Junkai Zhang +3Large Language Model Unlearning Robust Multimodal Learning
Null Space Constrained Contrastive Visual Forgetting for MLLM Unlearning
May 7, 2026Yuhang Wang, Zhenxing Niu, Haoxuan Ji +3Catastrophic Forgetting Multimodal Learning
Retain-Neutral Surrogates for Min-Max Unlearning
May 7, 2026Junhao Cai, Dohun Kim, Dowon Kim +4Several Approximate Unlearning Strategies Time-Step-Wise Learnable Surrogate Gradient Function
Do Neural Operators Forget Geometry? The Forgetting Hypothesis in Deep Operator Learning
May 7, 2026Yanming Xia, Angelica I. Aviles-RiveroNeural Operators Geometric Deep Learning

May 13, 2026 · cs.CVJ/K move · Enter open · S save

Unlocking Patch-Level Features for CLIP-Based Class-Incremental Learning

Hao Sun, Zi-Jun Ding, Da-Wei Zhou

School of Artificial Intelligence, Nanjing University · State Key Laboratory for Novel Software Technology, Nanjing University

Class-Incremental Learning (CIL) enables models to continuously integrate new knowledge while mitigating catastrophic forgetting. Driven by the remarkable generalization of CLIP, leveraging pre-trained vision-language models has become a dominant paradigm in CIL. However, current work primarily focuses on aligning global image embeddings (i.e., [CLS] token) with their corresponding text prompts (i.e., [EOS] token). Despite their good performance, we find that they discard the rich patch-level semantic information inherent in CLIP's encoders. For instance, when recognizing a rabbit, local patches may encode its distinctive cues, such as long ears and a fluffy tail, which can provide complementary evidence for recognition. Based on the above observation, we propose SPA (Semantic-guided Patch-level Alignment) for CLIP-based CIL, which aims to awaken long-neglected local representations within CLIP. Specifically, for each class, we first construct representative and diverse visual samples and feed them to GPT-5 as visual guidance to generate class-wise semantic descriptions. These descriptions are used to guide the selection of discriminative patch-level visual features. Building upon these selected patches, we further employ optimal transport to align selected patch tokens with semantic tokens from class-wise descriptions, yielding a structured cross-modal alignment that improves recognition. Furthermore, we introduce task-specific projectors for effective adaptation to downstream incremental tasks, and sample pseudo-features from stored class-wise Gaussian statistics to calibrate old-class representations, thereby mitigating catastrophic forgetting. Extensive experiments demonstrate that SPA achieves state-of-the-art performance.

Domain Incremental Learning Spatial Patching Visual Embeddings Large Vision Language Models

Open paper Ask about it PDF