通知：联邦节假日调休：哥伦布日 / 原住民日（Columbus Day / Indigenous Peoples' Day），今日（13日）无更新。通知：联邦节假日调休：哥伦布日 / 原住民日（Columbus Day / Indigenous Peoples' Day），今日（13日）无更新。
arXiv 2602.03473cs.LGcs.CV
将Bi-Level路由混合专家扩展到300+任务的持续学习
Scaling Continual Learning to 300+ Tasks with Bi-Level Routing Mixture-of-Experts
School of Computing and Data Science, The University of Hong Kong（计算与数据科学学院，香港大学）；Center for Embodied Artificial Intelligence and Computer Vision, Shenzhen Loop Area Institute（具身人工智能与计算机视觉中心，深圳环宇区研究所）
Continual learning, especially class-incremental learning (CIL), on the basis of a pre-trained model (PTM) has garnered substantial research interest in recent years. However, how to effectively learn both discriminative and comprehensive feature representations while maintaining stability and plasticity over very long task sequences remains an open problem. We propose CaRE, a scalable {C}ontinual Le{a}rner with efficient Bi-Level {R}outing Mixture-of-{E}xperts (BR-MoE). The core idea of BR-MoE is a bi-level routing mechanism: a router selection stage that dynamically activates relevant task-specific routers, followed by an expert routing phase that dynamically activates and aggregates experts, aiming to inject discriminative and comprehensive representations into every intermediate network layer. On the other hand, we introduce a challenging dataset, OmniBenchmark-1K, for CIL performance evaluation on very long task sequences with hundreds of tasks. Extensive experiments show that CaRE demonstrates leading performance across a variety of datasets and task settings, including commonly used CIL datasets with classical CIL settings (e.g., 5-20 tasks). To the best of our knowledge, CaRE is the first continual learner that scales to very long task sequences (ranging from 100 to over 300 non-overlapping tasks), while outperforming all baselines by a large margin on such task sequences. We hope that this work will inspire further research into continual learning over extremely long task sequences. Code and dataset are publicly released at https://github.com/LMMMEng/CaRE.
FlyPrompt: Brain-Inspired Random-Expanded Routing with Temporal-Ensemble Experts for General Continual Learning
School of Life Sciences, IDG/McGovern Institute for Brain Research, Tsinghua University（生命科学学院，IDG/麦克格雷文脑科学研究院，清华大学）；Department of Psychological and Cognitive Sciences, Tsinghua University（心理学与认知科学系，清华大学）；School of Medicine, Shenzhen Campus of Sun Yat-Sen University（中山大学深圳校区医学学院）
Stable Routing for Mixture-of-Experts in Class-Incremental Learning
State Key Laboratory of Novel Software Technology, Nanjing University（南京大学新型软件技术国家重点实验室）；School of Artificial Intelligence, Nanjing University（南京大学人工智能学院）
CL-MoE: Enhancing Multimodal Large Language Model with Dual Momentum Mixture-of-Experts for Continual Visual Question Answering
School of Computer Science and Technology, East China Normal University（华东师范大学计算机科学与技术学院）；Shanghai Open University（上海开放大学）；ZhuQingTing Data Technology (Zhejiang) Co., Ltd（朱清庭数据科技（浙江）有限公司）
University of Southern California（南加州大学）；AWS AI（亚马逊云科技人工智能部门）
The mixture of Expert (MoE) parallelism is a recent advancement that scales up the model size with constant computational cost. MoE selects different sets of parameters (i.e., experts) for each incoming token, resulting in a sparsely-activated model. Despite several successful applications of MoE, its training efficiency degrades significantly as the number of experts increases. The routing stage in MoE relies on the efficiency of the All2All communication collective, which suffers from network congestion and has poor scalability. To mitigate these issues, we introduce SMILE, which exploits he…
Hierarchical-Task-Aware Multi-modal Mixture of Incremental LoRA Experts for Embodied Continual Learning
Ping An Technology (Shenzhen) Co., Ltd.（平安科技（深圳）有限公司）；Tsinghua Shenzhen International Graduate School（清华大学深圳国际研究生院）；Tsinghua University（清华大学）；Huazhong University of Science and Technology（华中科技大学）
Enhancing Online Continual Learning with Plug-and-Play State Space Model and Class-Conditional Mixture of Discretization
Harbin Institute Of Technology（哈尔滨工业大学）；King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）；Harbin Institute Of Technology (Shenzhen)（哈尔滨工业大学（深圳））；University of Oxford（牛津大学）
University of Oulu（奥卢大学）；Nanyang Technological University（南洋理工大学）；ByteDance（字节跳动）；National University of Defense Technology（国防科技大学）
The goal of Few-Shot Continual Learning (FSCL) is to incrementally learn novel tasks with limited labeled samples and preserve previous capabilities simultaneously, while current FSCL methods are all for the class-incremental purpose. Moreover, the evaluation of FSCL solutions is only the cumulative performance of all encountered tasks, but there is no work on exploring the domain generalization ability. Domain generalization is a challenging yet practical task that aims to generalize beyond training domains. In this paper, we set up a Generalized FSCL (GFSCL) protocol involving both class- an…
The Mixture-of-Experts (MoE) technique can scale up the model size of Transformers with an affordable computational overhead. We point out that existing learning-to-route MoE methods suffer from the routing fluctuation issue, i.e., the target expert of the same input may change along with training, but only one expert will be activated for the input during inference. The routing fluctuation tends to harm sample efficiency because the same input updates different experts but only one is finally used. In this paper, we propose StableMoE with two training stages to address the routing fluctuation…
Dynamic Mixture of Curriculum LoRA Experts for Continual Multimodal Instruction Tuning
Department of Computer Science and Technology, BNRist, Tsinghua University, Beijing, China（计算机科学与技术系，BNRist，清华大学，北京，中国）；Alibaba Group, Hangzhou, China（阿里巴巴集团，杭州，中国）
Scene-Adaptive Continual Learning for CSI-based Human Activity Recognition with Mixture of Experts
Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University（香港理工大学电子与电气工程系）；School of Computer Science and Engineering, The Macau University of Science and Technology（澳门科学理工学院计算机科学与工程学院）
Beijing Institute of Technology（北京理工大学）；Microsoft Corporation（微软公司）；Peking University（北京大学）；Microsoft Research（微软研究院）
Sparse mixture of experts provides larger model capacity while requiring a constant computational overhead. It employs the routing mechanism to distribute input tokens to the best-matched experts according to their hidden representations. However, learning such a routing mechanism encourages token clustering around expert centroids, implying a trend toward representation collapse. In this work, we propose to estimate the routing scores between tokens and experts on a low-dimensional hypersphere. We conduct extensive experiments on cross-lingual language model pre-training and fine-tuning on do…
Dynamic Mixture of Latent Memories for Self-Evolving Agents
The Chinese University of Hong Kong（香港中文大学）；University of Oxford（牛津大学）；Nanyang Technological University（南洋理工大学）；University of Edinburgh（爱丁堡大学）；Shanghai Jiao Tong University（上海交通大学）
Conditional Capacity and Routing in Mixture-of-Experts Particle Transformers
University of California San Diego（加州大学圣迭戈分校）；University of Illinois at Chicago（伊利诺伊大学芝加哥分校）；Fermi National Accelerator Laboratory（费米国家加速器实验室）；University of California Davis（加州大学戴维斯分校）
In regression tasks the distribution of the data is often too complex to be fitted by a single model. In contrast, partition-based models are developed where data is divided and fitted by local models. These models partition the input space and do not leverage the input-output dependency of multimodal-distributed data, and strong local models are needed to make good predictions. Addressing these problems, we propose a binary tree-structured hierarchical routing mixture of experts (HRME) model that has classifiers as non-leaf node experts and simple regression models as leaf node experts. The c…
SoftMoE: Soft Differentiable Routing for Mixture-of-Experts in LLMs
AGH University of Krakow, Poland（克拉科夫AGH大学）；Faculty of Mathematics（数学系）；Computer Science, Jagiellonian University, Poland（计算机科学系，杰哥利安大学，波兰）；Centre for Credible Artificial Intelligence, Warsaw University of Technology（可信人工智能中心，华沙技术大学）
