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 →

Denser $\neq$ Better: Limits of On-Policy Self-Distillation for Continual Post-Training
Jul 2, 2026Meng Wang, Haohan Zhao, Wenzhuo Liu +7Unsupervised On-Policy Self-Distillation On-Policy Distillation
LASER: A Corrective Lens for LVLMs via Visual Attention Preservation and Sink Suppression
Jul 2, 2026Bowen Yuan, Zijian Wang, Yadan Luo +2Large Vision Language Models Lens
Multi-Head Recurrent Memory Agents
Jul 1, 2026Jiatong Li, Samuel Yeh, Sharon LiRecurrent Model Efficient Long-Context Inference
Rosetta: Composable Native Multimodal Pretraining
Jul 1, 2026Xiangyue Liu, Zijian Zhang, Miles Yang +3Multimodal Pretraining Input Modality
ASPIRE: Agentic /Skills Discovery for Robotics
Jun 30, 2026Runyu Lu, Yubo Wu, Ethan Kou +11Human-To-Robot Transfer Robotics
Creating Intelligence: A Computational Foundation for AGI
Jun 30, 2026Peter OvermannDense Associative Memory Neuromorphic Hardware
FastDSAC: Enhancing Policy Plasticity via Constrained Exploration for Scalable Humanoid Locomotion
Jun 30, 2026Guanchen Lu, Yajuan Dun, Yi Zhou +4Deep Reinforcement Learning Efficient Exploration
Surprise as a Signal for Plasticity and Metacognition
Jun 30, 2026Louis MouchonEpisodic Experiences Plasticity
CLIMB: Centroid-Based Hierarchical Memory for Online Continual Self-Supervised Learning
Jun 30, 2026Julien Lefebvre, Stefan Duffner, Mathieu LefortEfficient Continual Learning Self-Supervised
Rethinking the Role of Feature Engineering and Learning Strategies in Few-Shot Hidden Emotion Recognition
Jun 30, 2026Xiaochuan Guo, Jihao Gu, Haixu Liu +6Emotion Recognition Temporal Deep Learning Framework
Multisensory Continual Learning: Adapting Pretrained Visuomotor Policies to Force
Jun 29, 2026Jaden Clark, Changhao Wang, Yihuai Gao +5Visuomotor Policy Robotic Datasets
Revocable Learned State via Process Sidecars
Jun 29, 2026John SweeneyCatastrophic Forgetting Rollback
Convergence of Continual Learning in Homogeneous Deep Networks
Jun 29, 2026Matan Schliserman, Gon Buzaglo, Itay Evron +1Efficient Continual Learning Singular Learning Theory
Few-Shot Domain Incremental Learning via Continual Vision-Language Consolidation
Jun 29, 2026Naeem Paeedeh, Mahardhika Pratama, Wolfgang Mayer +3Domain Incremental Learning Vision-Language Model Adaptation
Neural Subspace Reallocation: Continual Learning as Retrieval-Based Subspace Memory Management
Jun 29, 2026Byeong Hoon YoonEfficient Continual Learning Continual Learning Methods
Parametric Skills
Jun 29, 2026Xuan Zhao, Haonan He, Qingyu Yang +5Unsupervised Skill Discovery Agentic Tool Use
Theory of Continual Learning Against Data Poisoning Attacks
Jun 29, 2026Yiting Hu, Lingjie DuanEfficient Continual Learning Data Poisoning
Robust Trajectory Distillation: Hybrid Reweighting Meets Teacher-Inspired Targets
Jun 29, 2026Kaifeng Chen, Lechao Cheng, Jiyang Li +6Noisy Labels Reweighting
The Forgetting-Retention Dilemma: Certified Unlearning Theory in Continual Learning
Jun 29, 2026Yiting Hu, Lingjie Duan, Qian ZhangEfficient Continual Learning Unlearning Aims
Anti-Collapse Dynamics and the Emergence of Multi-Time-Scale Learning in Recurrent Neural Networks
Jun 28, 2026Lorenzo LiviRecurrent Neural Networks Learning Rates
Prototype Latent World Model Replay for Class-Incremental Learning
Jun 28, 2026Weizhi Nie, Hui Wang, Weijie Wang +1Domain Incremental Learning Learnable Prototypes
Selective Memory Retention for Long-Horizon LLM Agents
Jun 28, 2026Pranath ReddyRetention
Fisher-Routed Mixture of Experts for Federated Class-Incremental Learning
Jun 27, 2026Wenhao Yuan, Chenchen Lin, Jian Chen +3Federated Learning Domain Incremental Learning
DexCompose: Reusing Dexterous Policies for Multi-Task Manipulation with a Single Hand
Jun 26, 2026Dihong Huang, Zhenyu Wei, Zhuxiu Xu +3Robotic Manipulation Policies Real-World Manipulation Tasks
Agent-Native Immune System: Architecture, Taxonomy, and Engineering
Jun 26, 2026Bo Shen, Lifeng Chang, Tianyuan Wei +7Defense Strategies Taxonomy
When One Adapter Speaks for Many: Discovering Low-Rank Redundancy in Continual Fine-Tuning
Jun 26, 2026Tanguy Dieudonné, Giulia Lanzillotta, Enis Simsar +2Low-Rank Adaptation Adapters Continual Fine-Tuning
Continual Learning for Sequential Personalization of Small Language Models: A Stability Monitoring Analysis
Jun 26, 2026Thomas S. Paula, Lucas S. Kupssinskü, Rodrigo C. BarrosEfficient Continual Learning Small Language Models
Continual Robot Policy Learning via Variational Neural Dynamics
Jun 25, 2026Jiaxu Xing, Zhiyuan Zhu, Yunfan Ren +4Robot Policies Continual Learning Methods
Data-Free Reservoir Features for Efficient Long-Horizon Cold-Start Continual Learning
Jun 25, 2026Augustinas Jučas, Yangchen PanDomain Incremental Learning Efficient Continual Learning
From Weights to Features: SAE-Guided Activation Regularization for LLM Continual Learning
Jun 25, 2026Evan Ning, Wei Xue, Dong Lou +1Catastrophic Forgetting Continual Learning Methods
Forget, Anticipate and Adapt: Test Time Training for Long Videos
Jun 25, 2026Rajat Modi, Sebastian Noel, Xin Liang +1Temporal Deep Learning Framework Fine-Grained Video Understanding
Natural Ungrokking: Asymmetric Control of Which Rules Survive Pretraining
Jun 24, 2026Juliana Li, Diya SreedharModel Pretraining Grokking
Geometry-Anchored Transport Framework for Exemplar-Free Class-Incremental Learning
Jun 24, 2026Hongye Xu, Bartosz KrawczykDomain Incremental Learning Semantic-Geometric Representations
Stagnant Neuron: Towards Understanding the Plasticity Loss in Multi-Agent Reinforcement Learning Value Factorization Methods
Jun 24, 2026Zhengzhu Liu, Zeming Gao, Haoyuan Qin +7Multi-Agent Reinforcement Learning Plasticity
The Gentle Collapse: Distributional Metrics for Continual Learning
Jun 23, 2026Ahmed Anwar, Andreas Wagner, Federico Raue +2Catastrophic Forgetting Retraining
GCT-MARL: Graph-Based Contrastive Transfer for Sample-Efficient Cooperative Multi-Agent Reinforcement Learning
Jun 23, 2026Animesh Animesh, Satheesh K Perepu, Kaushik DeyMulti-Agent Reinforcement Learning Iterative Co-Training
Erased, but Not Gone: Output Forgetting Is Not True Forgetting
Jun 23, 2026Teresa Pui Yee Yong, Win Kent Ong, Chee Seng ChanForgetting Catastrophic Forgetting
Adaptive Hebbian Memory Routing in Vision Transformers for Few-Shot Learning
Jun 23, 2026Mohammed Yusuf Mujawar, Noorbakhsh Amiri GolilarzFew-Shot Learning Self-Supervised Vision Transformers
Can Scale Save Us From Plasticity Loss in Large Language Models?
Jun 23, 2026J. Fernando Hernandez-Garcia, Tomás Figliolia, Beren MillidgeLarge Models Plasticity
Parallel Manifold Steering: Efficient Adaptation of Large Associative Memories via Residual Energy Shaping
Jun 23, 2026Kanishk AwadhiyaTransformer Residual Streams Dense Associative Memory
Towards Continuous Power Forecasting: Practical Continual Learning for Real-World Energy Systems in Nonstationary Time Series
Jun 23, 2026Yujiang He, Frederic Uhrweiller, Bernhard SickElectricity Price Forecasting Efficient Continual Learning
Fast and Slow Variational Continual Learning
Jun 22, 2026Subarnaduti Paul, Yohan Jung, Mohammad Emtiyaz Khan +3Efficient Continual Learning Continual Learning Methods
Forget Without Compromise: Nexus Sampling for Streaming KV-Cache Eviction Under Fixed Budgets
Jun 22, 2026Duc Duong, Hoang Anh Duy Le, Jianwen Xie +2Key-Value Cache Eviction Forgetting
RECALL: Recovery Experience Collection for Active Lifelong Learning in Vision-Language-Action Models
Jun 22, 2026Ulas Berk Karli, Tesca FitzgeraldVision-Language-Action Models Imitation Learning
CADRE: Stable, Parameter Efficient Adaptation of Medical Vision Language Models with Bounded Forgetting and Prior Drift
Jun 22, 2026Amrita Singh, Rishabh JhaVision-Language Model Adaptation Medical Vision-Language Models
Incremental Learning in Mirror Flows
Jun 22, 2026Raphaël Berthier, Loucas Pillaud-VivienMirror Descent Domain Incremental Learning
Attention-Spectrum Regularization for Replay-Free Continual Multimodal LLMs
Jun 22, 2026Chuangxin Zhao, Canran Xiao, Siyuan Ma +5Multi-Modal Large Language Models Cross-Modal Attention
Black-Box Continual Learning for Vision-Language Models
Jun 22, 2026Yuting Li, Weihang Fang, Haoyuan Gao +4Efficient Continual Learning Continual Learning Methods
Domain-incremental audio classification using domain-specific experts and prototype classifier
Jun 22, 2026Jongyeon Park, Do-Hyeon Lim, Sang-won Park +4Domain Incremental Learning Speech Separation
SamatNext v0.2-B: An Exploratory Study of RMS-Normalized Hybrid Decoders for Curriculum Retention in Small Code Models
Jun 20, 2026Samat ZharassovAutoregressive Transformers Catastrophic Forgetting
Distilling a Modular Reservoir Through a Genomic Bottleneck
Jun 20, 2026Mani Hamidi, Sina Khajehabdollahi, Charley M. Wu +1Reservoir Computing Recurrent Neural Networks
Social World Model for Lifelong Social Intelligence
Jun 19, 2026Yu LuoMultilingual Agents Continual Learning Methods
Task-Differentiated Atomic Skill Expansion and Routing for Continual Learning Across Highly Heterogeneous Tasks
Jun 19, 2026Jiacheng Wang, Xinjia He, Qi Ding +5Efficient Continual Learning Continual Learning Methods
Gradient-Free Warm-Start Library Recovery: an Amortized-Regret Separation
Jun 19, 2026Jianwei LouLearning-Augmented Algorithms Cold-Start
SLeDGe: Semi-Supervised Learning on Data Streams with Graph Structure Learning
Jun 19, 2026Heechan Moon, Kijung ShinSemi-Supervised Learning Graph Representation Learning
Is Our Benchmark Enough? An Analysis of Continual Learning for MLLMs
Jun 18, 2026Van-Tuan Tran, Shruthi Gowda, Merim Dzaferagic +1Efficient Continual Learning Multi-Modal Large Language Models
Provably Sub-Linear Two-Timescale NeuroEvolution with Online Plasticity
Jun 18, 2026Shishen Lin, Yixin ChenNeural Control Learning-Augmented Algorithms
Sparsity, Superposition, and Forgetting: A Mechanistic Study of Representation Retention in Continual Learning
Jun 18, 2026Jan Wasilewski, Jędrzej Kozal, Michał Woźniak +1Catastrophic Forgetting Forgetting
Hybrid ANN-SNN Pipeline with Local Plasticity
Jun 18, 2026Denis Larionov, Khairutin Shtanchaev, Mikhail Kiselev +2Spiking Neural Networks Binary Spikes
StreamKL: Fast and Memory-Efficient KL Divergence for Boosting Attention Distillation
Jun 18, 2026Guangda Liu, Yiquan Wang, Chengwei Li +6Kullback-Leibler Divergence Graphics Processing Unit Kernels

Jul 2, 2026 · cs.LGJ/K move · Enter open · S save

Denser $\neq$ Better: Limits of On-Policy Self-Distillation for Continual Post-Training

Meng Wang, Haohan Zhao, Wenzhuo Liu, Lu Yang+6

Centre for Artificial Intelligence and Robotics, HKISI, CAS · Institute of Automation, CAS · University of Chinese Academy of Sciences · Nanjing University of Science and Technology

Continual post-training enables foundation models to acquire new knowledge while preserving existing capabilities. Recent work suggests that on-policy learning can mitigate forgetting, with on-policy self-distillation emerging as a particularly attractive approach. In this work, we revisit this optimistic view through self-distillation policy optimization (SDPO). Our experiments show that SDPO can accelerate in-domain specialization when teacher signals are stable and well aligned, but it struggles to generalize to out-of-distribution scenarios. In continual post-training, SDPO exhibits stronger forgetting and can even collapse, whereas on-policy reinforcement learning methods such as GRPO adapt more conservatively and better preserve prior capabilities. Further analyses reveal that denser self-distillation induces larger drift in both parameter space and response space, and can amplify high-frequency formatting artifacts through a self-reinforcing teacher--student loop. These findings suggest that on-policy data alone is insufficient for continual learning. Dense self-distillation can accelerate specialization when teacher targets are stable and token-level supervision is reliable, but it should not be treated as a default stabilizer for continual post-training. Our code is available at https://github.com/Moenupa/SDPO-CL.

Unsupervised On-Policy Self-Distillation On-Policy Distillation Efficient Continual Learning LLM Post-Training Methods Forgetting

Open paper Ask about it PDF