Latest Continual Learning Research Papers

The newest Continual Learning papers from across the field — arXiv, NeurIPS, CVPR, Nature, and more — refreshed daily and ranked by relevance. Distill AI tracks Continual Learning so you don’t have to: get the standout work delivered to your inbox every morning, with 2-sentence summaries and the option to chat with any paper.

Recent papers

• Online Variance Reduction for Domain Adaptation on Streaming Data
  Andrea Napoli · arXiv · Jul 22, 2026

  This paper studies the problem of stochastic variance reduction (SVR) for the maximum mean discrepancy (MMD) and correlation alignment (CORAL) loss functions. Although various offline SVR algorithms for these losses have been proposed, thes…

• AlphaWiSE: Adaptive Weight Interpolation for Continual Multimodal Representation Learning
  Sarthak Jain, Qiran Hu, Zhen Zhu, Yaoyao Liu · arXiv · Jul 16, 2026

  Multimodal models such as CLIP learn a shared embedding space for cross-modal retrieval, but continual adaptation to sequentially arriving data can disrupt the cross-modal alignment acquired from earlier phases. Conventional continual-learn…

• The write-cost bottleneck: energy constraints on continual learning in brains and machines
  Bingru Xu, Hao Shen, Yuguo Yu · Cognitive Neurodynamics · Jul 16, 2026
• Leveraging Textual Semantic Guidance for Few-Shot Class-Incremental Learning
  Yuqiao Xu, Hantao Yao, Lu Yu, Changsheng Xu · ACM Transactions on Multime... · Jul 15, 2026

  Few-shot class-incremental learning (FSCIL) aims to continually learn new knowledge about few-shot novel classes while retaining the previously learned knowledge of old classes. With the rapid development of vision-language models ( e.g. , …

• TriA Pipeline: A Large-Scale Automatic Audio Annotation Pipeline For Audio Classification In Specific Scenarios
  Hong Lyu, Mingru Yang, Qianhua He, Yanxiong Li et al. · arXiv · Jul 7, 2026

  There are some datasets of varying scales for audio classification (AC) applied to different tasks. However, annotated data is limited for most scenarios, such as domestic environments. To address this challenge, we propose an $\textbf{A}$u…

• Attention-based Experience Replay Framework for Continual Learning of Agnostic Time Series Forecasting Models
  Quentin Besnard, Nicolas Ragot · HAL (Le Centre pour la Comm... · Jul 6, 2026

  International audience...

• Convergence of Continual Learning in Homogeneous Deep Networks
  Matan Schliserman, Gon Buzaglo, Itay Evron, Daniel Soudry · arXiv · Jun 29, 2026

  We characterize weakly regularized continual classification in homogeneous models as sequential projections onto task margin sets. This result generalizes prior analyses restricted to either stationary (single-task) deep models or continual…

• Learning from Mistakes: Rollout-Retrieval Lifelong Policy Learning for Autonomous Driving
  Cheng Gong, Haoyang Wang, Chao Lu, Zirui Li et al. · arXiv · Jun 29, 2026

  Autonomous driving policies should be able to improve continually as deployment exposes them to increasingly diverse and long-tail traffic situations. However, most learning-based policies are trained or fine-tuned on expert demonstrations …

• RECALL: Recovery Experience Collection for Active Lifelong Learning in Vision-Language-Action Models
  Ulas Berk Karli, Tesca Fitzgerald · arXiv · Jun 22, 2026

  Vision-Language-Action (VLA) models are commonly fine-tuned through passive imitation learning, where additional demonstrations are collected for tasks where the policy performs poorly. This approach incurs several downsides: it requires th…

• Hedgementation = Hedgerow Segmentation: A Remote Sensing Benchmark
  Nathan Senyard, Salem Hamdani, Astrid Zhang, Derek Wang et al. · arXiv · Jun 22, 2026

  We propose Hedgementation: a new benchmark to evaluate machine learning models for hedgerow mapping from remote sensing data at country scale and 10m$^2$ spatial resolution. We combine and harmonize multiple remote sensing data products and…

• Scaling Linear Mode Connectivity and Merging to Billion Parameter Pretrained Transformers
  Tianyi Li, Zhiqiang Shen · arXiv · Jun 22, 2026

  Linear mode connectivity (LMC) provides a promising foundation for understanding and merging independently trained neural networks, but existing methods typically optimize the interpolation path from only one model endpoint, limiting their …

• The Stable Recovery Manifold: Geometric Principles Governing Recoverability in Continual Learning
  Ayushman Trivedi, Bhavika Melwani · arXiv · Jun 11, 2026

  Catastrophic forgetting is often viewed as the destruction of previously learned knowledge during sequential learning. Building on the Accessibility Collapse framework, we investigate the geometric structure of recoverability in continual l…

• Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks
  Mengyu Zheng, Kai Han, Boxun Li, Haiyang Xu et al. · arXiv · Jun 10, 2026

  General-purpose agents such as OpenClaw are increasingly used as autonomous tool users, but their coding ability is difficult to measure under SWE-bench: a generic agent does not by itself satisfy the clean Docker workspace, patch, and pred…

• OncoTraj: a public benchmark for longitudinal resistance prediction in EGFR-mutant non-small-cell lung cancer on osimertinib
  Abhijoy Sarkar, Aarchi Singh Thakur · arXiv · Jun 9, 2026

  Resistance to first-line osimertinib in EGFR-mutant non-small-cell lung cancer (NSCLC) is the canonical example of predictable clonal evolution under therapeutic pressure, yet no public benchmark exists for training or evaluating computatio…

• Preserving Plasticity in Continual Learning via Dynamical Isometry
  Andries Rosseau, Robert Müller, Ann Nowé · ICML 2026 · Jun 8, 2026

  Continual training of deep neural networks under non-stationarity often leads to a progressive loss of plasticity, eventually limiting further learning. We relate plasticity to the empirical Neural Tangent Kernel, and identify dynamical iso…

• Sparse Subspace-to-Expert Sharing for Task-Agnostic Continual Learning
  Fatema Siddika, Md Anwar Hossen, Tanwi Mallick, Ali Jannesari · arXiv · Jun 5, 2026

  Continual learning in Large Language Models (LLMs) is hindered by the plasticity-stability dilemma, where acquiring new capabilities often leads to catastrophic forgetting of previous knowledge. Existing methods typically treat parameters u…

• Unsupervised Continual Clustering via Forward-Backward Knowledge Distillation
  Mohammadreza Sadeghi, Sareh Soleimani, Zihan Wang, Narges Armanfard · arXiv · Jun 5, 2026

  Unsupervised Continual Learning (UCL) aims to enable neural networks to learn sequential tasks without labels or access to past data. A major challenge in this setting is Catastrophic Forgetting, where models forget previously learned tasks…

• TailLoR: Protecting Principal Components in Parameter-Efficient Continual Learning
  Marius Dragoi, Ioana Pintilie, Alexandra Dragomir, Antonio Barbalau et al. · arXiv · Jun 4, 2026

  Parameter-efficient finetuning methods based on spectral decomposition have enabled progress in Continual Learning. In this paper we introduce TailLoR, which utilizes the singular bases U and V of the pre-trained weights as a fixed referenc…

• A Local Perturbation Theory for Cross-Domain Interference and Recovery in Multi-Domain RL
  Lei Yang, Siyu Ding, Deyi Xiong · arXiv · Jun 1, 2026

  Reinforcement learning (RL) post-training improves large language models (LLMs) on individual domains such as mathematical reasoning, code generation, question answering, and creative writing (CW), but training on one domain often degrades …

• AREA: Attribute Extraction and Aggregation for CLIP-Based Class-Incremental Learning
  Zhen-Hao Xie, Yu-Cheng Shi, Da-Wei Zhou · arXiv · May 27, 2026

  Class-Incremental Learning (CIL) is important in building real-world learning systems. In CLIP-based CIL, the model performs classification by comparing similarity between visual and textual embeddings obtained from template prompts, e.g., …

• MemoryBench: A Benchmark for Memory and Continual Learning in LLM Systems
  Qingyao Ai, Yichen Tang, Changyue Wang, Jianming Long et al. · arXiv.org · Oct 20, 2025

  Scaling up data, parameters, and test-time computation has been the mainstream methods to improve LLM systems (LLMsys), but their upper bounds are almost reached due to the gradual depletion of high-quality data and marginal gains obtained …

• BiLoRA: Almost-orthogonal Parameter Spaces for Continual Learning
  Hao Zhu, Yifei Zhang, Junhao Dong, Piotr Koniusz · Computer Vision and Pattern Recognition · Jun 10, 2025

  Continual learning requires models to learn tasks sequentially while maintaining a delicate balance between stability (retaining knowledge of previous tasks) and plasticity (adapting to new tasks). A key challenge is preventing interference…

• MLLM-CL: Continual Learning for Multimodal Large Language Models
  Hongbo Zhao, Fei Zhu, Meng Wang, Rundong Wang et al. · arXiv.org · Jun 5, 2025

  Recent Multimodal Large Language Models (MLLMs) excel in vision-language understanding but face challenges in adapting to dynamic real-world scenarios that require continuous integration of new knowledge and skills. While continual learning…

• CL-CaGAN: Capsule Differential Adversarial Continual Learning for Cross-Domain Hyperspectral Anomaly Detection
  Jianing Wang, Siying Guo, Zheng Hua, Runhu Huang et al. · IEEE Transactions on Geoscience and Remote Sensing · May 17, 2025

  Anomaly detection (AD) has attracted remarkable attention in hyperspectral image (HSI) processing fields, and most existing deep learning (DL)-based algorithms indicate dramatic potential for detecting anomaly samples through specific train…

• Knowledge Efficient Federated Continual Learning for Industrial Edge Systems
  Jiao Chen, Jiayi He, Jian Tang, Weihua Li et al. · IEEE Transactions on Network Science and Engineering · May 1, 2025

  Recent advances in federated learning (FL) primarily focus on addressing inter-client data heterogeneity, implicitly assuming static data within each client. However, this assumption is inadequate for industrial edge systems (IES), which op…

• Human-Guided Continual Learning for Personalized Decision-Making of Autonomous Driving
  Haohan Yang, Yanxin Zhou, Jingda Wu, Haochen Liu et al. · IEEE transactions on intelligent transportation systems (Print) · Apr 1, 2025

  Learning-based techniques hold considerable promise in achieving human-like autonomous driving. However, one deployed policy encounters difficulties in satisfying the drivers’ diverse decision-making preferences simultaneously. Meanwhile, t…

• Language Guided Concept Bottleneck Models for Interpretable Continual Learning
  Lu Yu, Haoyu Han, Zhe Tao, Hantao Yao et al. · Computer Vision and Pattern Recognition · Mar 30, 2025

  Continual learning (CL) aims to enable learning systems to acquire new knowledge constantly without forgetting previously learned information. CL faces the challenge of mitigating catastrophic forgetting while maintaining interpretability a…

• LoRA Subtraction for Drift-Resistant Space in Exemplar-Free Continual Learning
  Xuan Liu, Xiaobin Chang · Computer Vision and Pattern Recognition · Mar 23, 2025

  In continual learning (CL), catastrophic forgetting often arises due to feature drift. This challenge is particularly prominent in the exemplar-free continual learning (EFCL) setting, where samples from previous tasks cannot be retained, ma…

• From RAG to Memory: Non-Parametric Continual Learning for Large Language Models
  Bernal Jiménez Gutiérrez, Yiheng Shu, Weijian Qi, Sizhe Zhou et al. · International Conference on Machine Learning · Feb 20, 2025

  Our ability to continuously acquire, organize, and leverage knowledge is a key feature of human intelligence that AI systems must approximate to unlock their full potential. Given the challenges in continual learning with large language mod…

• Accurate Forgetting for Heterogeneous Federated Continual Learning
  Abudukelimu Wuerkaixi, Sen Cui, Jingfeng Zhang, Kunda Yan et al. · International Conference on Learning Representations · Feb 20, 2025

  Recent years have witnessed a burgeoning interest in federated learning (FL). However, the contexts in which clients engage in sequential learning remain under-explored. Bridging FL and continual learning (CL) gives rise to a challenging pr…