Task-Free Continual Learning

Follow this topic Ask about this topic

Latest papers

18 papers0 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Data-Free Continual Learning for World Action Model with Rectified Generative Replay
Oct 13, 2026Kaipeng Fang, Hangxu Liu, Chaojian Shi +5Task-Free Continual Learning Continual Robot Learning
University of Electronic Science and Technology of China · Shanghai AI Lab · Fudan University +3
Neural-Collapse-guided Task-Free Continual Anomaly Detection
Sep 3, 2026Xiaotong Kong, Chaoyang Song, Ziai Zhou +3Continual Anomaly Detection Continual Learning
Key Laboratory of Measurement and Control of CSE, Ministry of Education, School of Automation, Southeast University, Nanjing 210096, China
Unifying Detection and Adaptation in Task-Free Continual Learning
Aug 27, 2026Dezheng Han, Anbang Zhang, Zhihao Zhu +1Task-Free Continual Learning Continual Learning
School of Control Science and Engineering, Shandong University, Jinan, China · Department of ECE, The Hong Kong University of Science and Technology, Hong Kong · National Medicine-Engineering Interdisciplinary Industry-Education Integration Innovation Platform, Shandong University, Jinan, China +1
Relative Parameter Importance in Task-Agnostic Replay-Free Continual Learning
Aug 1, 2026Malavika Suresh, Ikechukwu Nkisi-Orji, Nirmalie WiratungaClass-Incremental Learning Regularization-Based Continual Learning
Robert Gordon University
UNIT: Unleash Large Language Models Potential for Graph Continual Learning
Jul 11, 2026Tairan Huang, Yili Wang, Beibei Hu +4Graph Representation Learning Continual Learning
Central South University Changsha, China · Hongkong University of Science and Technology (Guangzhou) Guangzhou, China · Hunan Institute of Engineering Changsha, Hunan
LargeMonitor: Monitoring Online Task-Free Continual Learning via Large Pretrained Models
Jun 8, 2026Mingqi Yuan, Xiaoquan Sun, Shihao Luo +1Distribution Shift Concept Drift
Agentic Intelligence Lab | HKU · Qicore Tech
Sparse Subspace-to-Expert Sharing for Task-Agnostic Continual Learning
Jun 5, 2026Fatema Siddika, Md Anwar Hossen, Tanwi Mallick +1Continual Learning for LLMs Mixture-of-Experts Language Models
Iowa State University, Ames, USA · Argonne National Laboratory, USA
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
PILOT: A Data-Free Continual Learning Approach for Real-Time Semantic Segmentation via Boundary Guidance
May 26, 2026Yujing Zhou, Prashant Shekhar, Thomas Yang +1Class-Incremental Learning Task-Free Continual Learning
Department of Mathematics, College of Arts and Sciences, Embry-Riddle Aeronautical University, Daytona Beach, FL 32114, USA · Department of Electrical Engineering and Computer Science, College of Engineering, Embry-Riddle Aeronautical University, Daytona Beach, FL 32114, USA
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
Stop Marginalizing My Dreams: Model Inversion via Laplace Kernel for Continual Learning
May 12, 2026Patryk Krukowski, Jacek Tabor, Przemysław Spurek +2Task-Free Continual Learning Inverse Problems
Jagiellonian University · IDEAS Research Institute
Is Prompt Selection Necessary for Task-Free Online Continual Learning?
Apr 6, 2026Seoyoung Park, Haemin Lee, Hankook LeeTask-Free Continual Learning Continual Learning
Sungkyunkwan University
Unlearning-based sliding window for continual learning under concept drift
Mar 15, 2026Michal Wozniak, Marek Klonowski, Maciej Maczynski +1Task-Free Continual Learning Concept Drift
Wroclaw University of Science and Technology Wrocław, Poland · Rochester Institute of Technology NY, USA
CARL-CXR: Continual Adapter-Based Routing for Task-Unknown Chest Radiograph Classification
Feb 17, 2026Muthu Subash Kavitha, Anas Zafar, Amgad Muneer +1Task-Incremental Learning Task-Free Continual Learning
Department of Imaging Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
SAILS: Segment Anything with Incrementally Learned Semantics for Task-Invariant and Training-Free Continual Learning
Feb 16, 2026Shishir Muralidhara, Didier Stricker, René SchusterTask-Free Continual Learning Continual Learning
German Research Center for Artificial Intelligence (DFKI) · RPTU – University of Kaiserslautern-Landau, Kaiserslautern
Knowledge-Aware Evolution for Task-Free Streaming Federated Continual Learning with Arbitrary Class Overlap
Jan 27, 2026Sixing Tan, Xianmin LiuContinual Learning Federated Continual Learning
Faculty of Computing Harbin Institute of Technology
Are Current Continual Learning Methods Truly Agnostic? Introducing OPRE, a Step Toward Agnostic Continual Learning
Nov 11, 2025Raphaël Bayle, Martial Mermillod, Robert M. FrenchContinual Learning Coreset Selection
Univ. Grenoble Alpes, Univ. Savoie Mont Blanc, CNRS, LPNC, Grenoble, France · LEAD-CNRS UMR 5022, U. de Bourgogne Europe, Dijon, France
Task-Agnostic Federated Continual Learning via Replay-Free Gradient Projection
Sep 25, 2025Seohyeon Cha, Huancheng Chen, Haris VikaloFederated Continual Learning Gradient Projection
Department of Electrical and Computer Engineering The University of Texas at Austin

Oct 13, 2026J/K move · Enter open · S save

Data-Free Continual Learning for World Action Model with Rectified Generative Replay

Kaipeng Fang, Hangxu Liu, Chaojian Shi, Yunsong Zhou+4

University of Electronic Science and Technology of China · Shanghai AI Lab · Fudan University+3

Task-Free Continual Learning Continual Robot Learning World Action Models Generative Replay

Open paper AskPDF arXiv

World action models (WAMs) built on pretrained video generation models adapt quickly to new robotic tasks, but they forget previously learned tasks under sequential fine-tuning. Experience replay (ER) mitigates such forgetting by rehearsing data of previous tasks, yet this data is often unavailable in robotics, where a policy is deployed as weights only and its training data is not shared along with it. In this work, we ask whether a WAM can achieve data-free continual learning by regenerating its own past. Our key observation is that a WAM can indeed autoregressively regenerate complete rollouts of previously learned tasks and replay them to mitigate forgetting. However, replaying such raw rollouts still lags far behind replaying real data, which we attribute to two issues. First, the WAM is unable to recognize task completion and keeps generating purposeless motion after the task is done. Second, under open-loop generation, the generated actions gradually drift away from the generated observations. To address both issues, we present rectified generative replay (R

^2

-WAM), which truncates generated rollouts at task completion with an agentic evaluator and filters out rollouts whose actions are physically inconsistent with the observations. On the four LIBERO suites and five real-world tasks, R

^2

-WAM reduces forgetting by over 90% relative to sequential fine-tuning and nearly matches ER without accessing any data from previous tasks. Our analysis further reveals that forgetting in WAMs concentrates in inverse dynamics modeling: a forgotten WAM still produces visually plausible observations of previous tasks while its generated actions fail. Project page: https://kaipengfang.github.io/r2-wam/