Adapter-Based Continual Learning

Latest papers

17 papers5 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

SARAM: Sparse Adapter Allocation with Reuse and Merging for Lifelong Robot Learning
Oct 17, 2026SeongJun Jeong, Chungwoo Lee, Gi-Cheon Kang +1Adapter-Based Continual Learning Continual Robot Learning
Seoul National University · Ajou University
Knowledge Interaction in Hypernetwork-based Continual Learning: Conflict and Composition
Oct 11, 2026Jiaqi Zheng, Yi Hu, Yadong Mu +1Continual Learning for LLMs Knowledge Conflicts in Language Models
Peking University · Norizon AI
PaLoRA: Paced Low-Rank Adaptation for Continual Learning
Oct 3, 2026Yuxuan Li, Fanhu Zeng, Hao TangContinual LoRA Continual Learning
School of Computer Science Peking University · Institute of Automation Chinese Academy of Sciences
Local Support Learning
Oct 1, 2026Assaf Ben-Kish, Akarsh Kumar, James Glass +1Continual Learning for LLMs Adapter-Based Continual Learning
Tel Aviv University · MIT CSAIL
MuLoRA: Spectrally Balanced Low-Rank Adaptation for Continual Learning
Oct 1, 2026Junkang LiuContinual Learning Low-Rank Adaptation
Tianjin University
Muon Can Outperform Dedicated Continual Learning Methods
Sep 21, 2026Sebastian George Sincari, Bogdan Alexandru Gheorghe, Antonio BarbalauContinual Learning Muon Optimizer
Faculty of Mathematics and Computer Science, University of Bucharest, Bucharest, Romania · Bitdefender, Bucharest, Romania
One Adapter, Many Tasks: Task-Conditioned Feature Transformations for Continual Learning
Aug 31, 2026Yunxiang Fu, Meng Lou, Yizhou YuClass-Incremental Learning Incremental Learning
School of Computing and Data Science The University of Hong Kong
Restoring Without Forgetting: Continual Learning Across Image Degradations
Aug 24, 2026Alif Ashrafee, Bartosz KrawczykAdapter-Based Continual Learning Image Restoration
Rochester Institute of Technology New York, USA
BPG: Balancing Plasticity and Generalization for Domain Incremental Learning
Aug 11, 2026Qiang Wang, Songlin Dong, Shaokun Wang +5Domain-Incremental Learning Incremental Learning
College of Artificial Intelligence, Xi’an Jiaotong University, Xi’an, China · Shenzhen University of Advanced Technology, Shenzhen, China · Harbin Institute of Technology, Shenzhen, China +1
Latent-LoRA: Compact Latent-Space Adapters with Gradient-Free Routing for Continual Learning
Jul 26, 2026Reza Rahimi Azghan, Gautham Krishna Gudur, Giulia Pedrielli +2Continual Learning for LLMs Continual LoRA
College of Health Solutions, Arizona State University, Phoenix, Arizona, USA · Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, Texas, USA · School of Computing and Augmented Intelligence, Arizona State University, Tempe, Arizona, USA +1
When One Adapter Speaks for Many: Discovering Low-Rank Redundancy in Continual Fine-Tuning
Jun 26, 2026Tanguy Dieudonné, Giulia Lanzillotta, Enis Simsar +2Continual Learning Low-Rank Adaptation
Department of Computer Science, ETH Zurich, Zurich, Switzerland.
Energy-Structured Low-Rank Adaptation for Continual Learning
May 26, 2026Longhua Li, Lei Qi, Qi Tian +1Continual Learning Low-Rank Adaptation
School of Computer Science and Engineering, Southeast University, Nanjing, China · Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, China · Huawei Technologies, Shenzhen, China
Low-Rank Adapters Initialization via Gradient Surgery for Continual Learning
May 12, 2026Joana Pasquali, Ramiro N. Barros, Arthur S. Bianchessi +7Gradient Interference Catastrophic Forgetting
MALTA, Machine Learning Theory and Applications Lab, PUCRS, Porto Alegre, Brazil · Kunumi Institute, Brazil
JumpLoRA: Sparse Adapters for Continual Learning in Large Language Models
Apr 17, 2026Alexandra Dragomir, Ioana Pintilie, Antonio Barbalau +6Continual Learning for LLMs Low-Rank Adaptation
Bitdefender · ETH Zurich · University of Bucharest
One Adapter for All: Towards Unified Representation in Step-Imbalanced Class-Incremental Learning
Mar 10, 2026Xiaoyan Zhang, Jiangpeng HeAdapter-Based Continual Learning Class-Incremental Learning
University of Michigan, Ann Arbor, Michigan, U.S.A · Indiana University, Bloomington, Indiana, U.S.A
From Isolation to Integration: Building an Adaptive Expert Forest for Pre-Trained Model-based Class-Incremental Learning
Feb 24, 2026Ruiqi Liu, Boyu Diao, Hangda Liu +3Adapter-Based Continual Learning Class-Incremental Learning
Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China · University of Chinese Academy of Sciences, Beijing, China
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

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

SARAM: Sparse Adapter Allocation with Reuse and Merging for Lifelong Robot Learning

SeongJun Jeong, Chungwoo Lee, Gi-Cheon Kang, Byoung-Tak Zhang

Seoul National University · Ajou University

Adapter-Based Continual Learning Continual Robot Learning Continual Learning for VLA Models Storage-Efficient Continual Learning

Open paper AskPDF arXiv

Lifelong robot learning requires acquiring new tasks sequentially without forgetting earlier ones. With large pre-trained vision-language-action (VLA) backbones, adapter-based methods effectively mitigate this challenge. However, their task-specific adapters and selection modules accumulate with the task stream, creating a scalability challenge in on-disk storage and deployment cost under fixed onboard resource budgets. We propose SARAM, a lifelong learning framework that limits storage growth while keeping GPU memory and per-step inference cost independent of the task stream length. For each new task, SARAM reuses frozen adapters from previous tasks and introduces new adapters only at sparsely selected layers, with a duplication penalty encouraging them to capture information not already represented by the adapter library. At deployment, a compact signature derived from backbone activation statistics identifies the task once per episode, and the corresponding task update is merged into the backbone, leaving only the backbone in the control loop. Across four LIBERO suites, SARAM matches or exceeds adapter-based baselines while adding up to 4.5x less on-disk state per task. GPU memory usage and control frequency remain comparable to those of the backbone as the task stream grows. Experiments on a real UR5 arm with a different backbone further demonstrate retention throughout a sequential task stream.