Layer-Selective Rehearsal Strategy

Follow this topic Ask about this topic

Momentum

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

Jul 6Week of Sep 21

Latest papers 14

All topics

Dynamic LoRA-Experts and Prototype-Ensemble Matching for Class-Incremental Learning
Sep 30, 2026Hongwei Zhao, Rui Liu, Yansong LiuClass-Incremental Learning Layer-Selective Rehearsal Strategy
School of Computer Science and Engineering, Beihang University
Hyperbolic Prototype Routing for Rehearsal-Free Class-Incremental Learning
Sep 30, 2026HongWei Zhao, Rui Liu, Yong ChenClass-Incremental Learning Learnable Prototypes
Beihang University · Beijing University of Posts and Telecommunications
Beyond Class Marginals: Bounding Rehearsal Gaps without Freezing Class Co-occurrence
Sep 22, 2026Congren Dai, Nat Roongjirarat, Fei YeLayer-Selective Rehearsal Strategy Deterministic Replay
Imperial College London · King’s College London · University of Electronic Science and Technology of China
DistMoE: Private-data Rehearsal-free Routing in Mixture-of-Experts for Distributed Instruction Tuning
Aug 10, 2026Mainak Singha, Niccolò Biondi, Elisa Ricci +1Multimodal Continual Instruction Tuning Mixture-Of-Experts
University of Trento, Italy · Fondazione Bruno Kessler, Italy · University of Bergamo, Italy
EnvACE: Internalizing Environment Dynamics via World Rehearsal for Agentic Reinforcement Learning
Aug 6, 2026Zishan Xu, Zhiyuan Yao, Yuxin Chen +9Agentic Reinforcement Learning Large Language Model Agents
Shanghai Jiao Tong University · Zhejiang University · National University of Singapore +4
Rehearse: Stepping Back from the Confidence Cliff in Self-Improving Autoresearch
Jul 30, 2026Jiazhen Ji, Shouhong DingRecursive Self-Improvement Self-Evaluation
Tencent
Rehearsed Multi-Agent Live Product Demonstrations with Real-Time Voice Question Answering
Jun 29, 2026Rahul Khedar, Mayank Malhotra, Avinash Karn +2Layer-Selective Rehearsal Strategy Browser Agent
PayPal AI
When Generator Replay Degrades: Projected Rehearsal Orchestration for Heterogeneous Federated Class-Incremental Learning
Jun 14, 2026Thinh T. H. Nguyen, Khoa D. Doan, Binh T. Nguyen +2Class-Incremental Learning Layer-Selective Rehearsal Strategy
VinUniversity, Hanoi, Vietnam · VNU-HCM, University of Science, Ho Chi Minh City, Vietnam · Technische Universität Berlin, Germany
T2S: A Rehearsal-Based Approach for Extraction-Resistant Model Watermarking
Jun 10, 2026Jian-Ping Mei, Weibin Zhang, Ao Yao +2Watermarking Layer-Selective Rehearsal Strategy
College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, 310023 China
Revisiting Prototype Rehearsal for Exemplar-Free Continual Learning: Manifold-Aware Boundary Sampling with Adaptive Class-Balanced Loss
Jun 4, 2026Hongye Xu, Bartosz KrawczykClass-Incremental Learning Learnable Prototypes
Chester F. Carlson Center for Imaging Science Rochester Institute of Technology
Internalize the Temperature: On-Policy Self-Distillation as Policy Reheater for Reinforcement Learning
May 30, 2026Xuewei Yang, Jiachen Yu, Jie Wu +3Unsupervised On-Policy Self-Distillation Large Language Model Reinforcement Learning
Tsinghua University
Don't Forget the Critic: Value-Based Data Rehearsal for Multi-Cyclic Continual Reinforcement Learning
May 21, 2026Benjamin Poole, Andrew Quinn, Li Yang +1Offline Reinforcement Learning Catastrophic Forgetting
Department of Computer Science University of North Carolina at Charlotte
Order-based Rehearsal Learning
May 6, 2026Yu-Xuan Tao, Tian-Zuo Wang, Zhi-Hua ZhouLayer-Selective Rehearsal Strategy Counterfactual Learning
National Key Laboratory for Novel Software Technology, Nanjing University, China · School of Artifcial Intelligence, Nanjing University, China
Lifecycle-Aware Federated Continual Learning in Mobile Autonomous Systems
Apr 22, 2026Beining Wu, Jun HuangFederated Learning Replay-Based Continual Learning
Department of Electrical Engineering and Computer Science, South Dakota State University, Brookings, 57006 SD

Sep 30, 2026, cs.LGJ/K move · Enter open · S save

Dynamic LoRA-Experts and Prototype-Ensemble Matching for Class-Incremental Learning

Hongwei Zhao, Rui Liu, Yansong Liu

School of Computer Science and Engineering, Beihang University

Class-Incremental Learning Layer-Selective Rehearsal Strategy

Open paper AskPDF arXiv

Class-Incremental Learning (CIL) aims to continuously learn new classes without forgetting previously acquired knowledge. Parameter-efficient fine-tuning with pre-trained models reduces parameter overhead but can suffer from cumulative interference and suboptimal alignment between inference samples and specialized modules. We propose Dynamic LoRA-Experts and Prototype-Ensemble Matching (DLEPEM), a two-stage rehearsal-free framework. DLEPEM allocates a task-specific LoRA-Expert for each incremental task to reduce cross-task interference, then combines frozen pre-trained-model prototypes with task-adaptive LoRA-Expert prototypes for reliable task-level discrimination. Experiments on standard CIL and Few-Shot CIL benchmarks demonstrate strong performance under the evaluated protocols.

Momentum

Related topics

Latest papers 14