Subspace-Based Continual Learning

Latest papers

8 papers1 paper in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

ROSE: Risk-Aware Orthogonal Subspace Navigation for Lifelong Knowledge Editing in Multimodal Large Language Models
Nov 6, 2026Lingyun Song, Ziyao Chen, Kang Pan +5Subspace-Based Continual Learning Knowledge Editing
School of Computer Science, Northwestern Polytechnical University, Xi’an · Shenzhen Research Institute of Northwestern Polytechnical University, Shenzhen · Independent Researcher +1
Stable-Plastic Subspace Construction for Differentially Private Continual LoRA
Oct 13, 2026Jin Liu, Ning Xi, Yinbin Miao +3Subspace-Based Continual Learning Continual Learning
Xidian University · Tianjin University
ReCAP: Retrieval-Guided Capability Reuse for Multimodal Continual Instruction Tuning
Sep 29, 2026Tao Hu, Zhinuo Zhou, Xialiang Tong +2Subspace-Based Continual Learning Continual Learning
School of Artificial Intelligence, Nanjing University · State Key Laboratory for Novel Software Technology, Nanjing University · Noah’s Ark Lab, Huawei Technologies
Efficient Online Continual Foundation Model Fine-Tuning for Predictive Process Monitoring
Aug 28, 2026Sjoerd van Straten, Marwan HassaniSubspace-Based Continual Learning Predictive Process Monitoring
Department of Mathematics and Computer Science, Eindhoven University of Technology, The Netherlands · Department of Mathematics and Computer Science, University of Wuppertal, Germany
OrthoSkillVLA: Continual Skill Learning via Gradient-Informed Skill Subspace Adaptation
Aug 20, 2026Jiaqi Wang, Zhou Fang, Qiongfeng Shi +1Subspace-Based Continual Learning Continual Learning for VLA Models
School of Computer Science and Engineering, Southeast University, China · Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications, Ministry of Education, China · School of Electronic Science and Engineering, Southeast University, China
Hierarchical Dual-Subspace Decoupling for Continual Learning in Vision-Language Models
May 8, 2026Mengxin Qin, Xiang Zhang, Kun Wei +2Class-Incremental Learning Vision-Language Models
School of Electronic Engineering, Xidian University Xi’an 710071, China
Task-Driven Subspace Decomposition for Knowledge Sharing and Isolation in LoRA-based Continual Learning
Feb 27, 2026Lingfeng He, De Cheng, Huaijie Wang +3Subspace-Based Continual Learning Continual Learning
State Key Laboratory of Integrated Services Networks, School of Telecommunications Engineering, Xidian University, Xi’an, China · School of Electronic Engineering, Xidian University, Xi’an, China · AUTHORERR: Missing \icmlaffiliation.
Sparse Subspace-to-Expert Sharing for Task-Agnostic Continual Learning
Jan 24, 2026Fatema Siddika, Md Anwar Hossen, Tanwi Mallick +1Subspace-Based Continual Learning Continual Learning for LLMs
Iowa State University, Ames, USA · Argonne National Laboratory, USA

Nov 6, 2026J/K move · Enter open · S save

ROSE: Risk-Aware Orthogonal Subspace Navigation for Lifelong Knowledge Editing in Multimodal Large Language Models

Lingyun Song, Ziyao Chen, Kang Pan, Xiaolin Han+4

School of Computer Science, Northwestern Polytechnical University, Xi’an · Shenzhen Research Institute of Northwestern Polytechnical University, Shenzhen · Independent Researcher+1

Subspace-Based Continual Learning Knowledge Editing Multimodal Knowledge Editing Catastrophic Forgetting Continual Learning for VLMs Incremental Learning

Open paper AskPDF arXiv

Multimodal Large Language Models (MLLMs) require continuous factual updates to stay current, yet lifelong knowledge editing remains a daunting challenge. The primary obstacle is the severe Locality Erosion and Catastrophic Forgetting, where sequential edits inevitably interfere with pre-trained capabilities and prior updates. In this paper, we propose ROSE, a Risk-aware Orthogonal Subspace navigation framework for lifelong knowledge Editing. ROSE addresses forgetting by aiming to restrict parameter updates to the orthogonal complement of previously edited subspaces. Crucially, it introduces a risk-guided mechanism that utilizes a dynamically computed risk mask to safeguard specific factual parameter subspaces essential for model stability. During inference, ROSE employs a multi-granularity knowledge integration strategy, featuring prototype-anchored semantic gating and perturbation-driven subspace fusion to precisely activate edited knowledge for relevant queries while limiting interference on unrelated inputs. Comprehensive experiments on two prominent multimodal benchmarks show that ROSE is competitive with state-of-the-art approaches across five key metrics, while maintaining outstanding stability over

1,000

sequential updates. Our code is available at https://github.com/sunlitsong/ROSE.