English
Related papers

Related papers: DIMoE-Adapters: Dynamic Expert Evolution for Conti…

200 papers

As foundational models reshape scientific discovery, a bottleneck persists in dynamical system reconstruction (DSR): the ability to learn across system hierarchies. Many meta-learning approaches have been applied successfully to single…

Machine Learning · Computer Science 2025-06-12 Roussel Desmond Nzoyem , Grant Stevens , Amarpal Sahota , David A. W. Barton , Tom Deakin

Catastrophic forgetting remains a major obstacle to continual learning in large language models (LLMs) and vision--language models (VLMs). Although Mixture-of-Experts (MoE) architectures offer an efficient path to scaling, existing…

Machine Learning · Computer Science 2026-05-21 Yang Liu , Toan Nguyen , Flora D. Salim

A generalist agent must continuously learn and adapt throughout its lifetime, achieving efficient forward transfer while minimizing catastrophic forgetting. Previous work within the dominant pretrain-then-finetune paradigm has explored…

Machine Learning · Computer Science 2026-05-29 Yuheng Lei , Sitong Mao , Shunbo Zhou , Hongyuan Zhang , Xuelong Li , Ping Luo

Mixture-of-Experts (MoE) presents a naturally compatible and scalable framework for multimodal learning, demonstrating strong adaptability across diverse modalities and tasks. Despite its growing success, a comprehensive and systematic…

Machine Learning · Computer Science 2026-05-28 Liangwei Nathan Zheng , Wei Emma Zhang , Olaf Maennel , Lin Yue , Weitong Chen

Diffusion policies have emerged as a powerful framework for robotic visuomotor control, yet they often lack the robustness to recover from subtask failures in long-horizon, multi-stage tasks and their learned representations of observations…

Robotics · Computer Science 2025-11-10 Baiye Cheng , Tianhai Liang , Suning Huang , Maanping Shao , Feihong Zhang , Botian Xu , Zhengrong Xue , Huazhe Xu

Test-time adaptation, which enables models to generalize to diverse data with unlabeled test samples, holds significant value in real-world scenarios. Recently, researchers have applied this setting to advanced pre-trained vision-language…

Computer Vision and Pattern Recognition · Computer Science 2024-10-17 Ce Zhang , Simon Stepputtis , Katia Sycara , Yaqi Xie

Recent advancements in general-purpose or domain-specific multimodal large language models (LLMs) have witnessed remarkable progress for medical decision-making. However, they are designated for specific classification or generative tasks,…

Computer Vision and Pattern Recognition · Computer Science 2024-09-04 Songtao Jiang , Tuo Zheng , Yan Zhang , Yeying Jin , Li Yuan , Zuozhu Liu

We introduce Dynamic Retrieval-Augmented Expert Networks (DRAE), a groundbreaking architecture that addresses the challenges of lifelong learning, catastrophic forgetting, and task adaptation by combining the dynamic routing capabilities of…

Robotics · Computer Science 2025-12-24 Yayu Long , Kewei Chen , Long Jin , Mingsheng Shang

End-to-end autonomous driving (E2E-AD) demands effective processing of multi-view sensory data and robust handling of diverse and complex driving scenarios, particularly rare maneuvers such as aggressive turns. Recent success of…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Zhenjie Yang , Yilin Chai , Xiaosong Jia , Qifeng Li , Yuqian Shao , Xuekai Zhu , Haisheng Su , Junchi Yan

Large-scale foundation models provide powerful feature representations for downstream object segmentation tasks. However, when adapted to specific tasks through the full-parameter fine-tuning, the enormous parameters being updated often…

Computer Vision and Pattern Recognition · Computer Science 2025-10-27 Yanguang Sun , Jiawei Lian , Jian Yang , Lei Luo

Among parallel decoding paradigms, diffusion large language models (dLLMs) have emerged as a promising candidate that balances generation quality and throughput. However, their integration with Mixture-of-Experts (MoE) architectures is…

Machine Learning · Computer Science 2026-02-03 Hao Mark Chen , Zhiwen Mo , Royson Lee , Qianzhou Wang , Da Li , Shell Xu Hu , Wayne Luk , Timothy Hospedales , Hongxiang Fan

Large Language Models (LLMs) have demonstrated remarkable abilities in tackling a wide range of complex tasks. However, their huge computational and memory costs raise significant challenges in deploying these models on resource-constrained…

Learning from non-stationary data streams subject to concept drift requires models that can adapt on-the-fly while remaining resource-efficient. Existing adaptive ensemble methods often rely on coarse-grained adaptation mechanisms or simple…

Contemporary machine learning models, including large language models, exhibit remarkable capabilities in static tasks yet falter in non-stationary environments due to rigid architectures that hinder continual adaptation and lifelong…

Machine Learning · Computer Science 2026-05-15 Akbar Anbar Jafari , Cagri Ozcinar , Gholamreza Anbarjafari

Finding the optimal configuration of Sparse Mixture-ofExperts (SMoE) that maximizes semantic differentiation among experts is essential for exploiting the full potential of MoE architectures. However, existing SMoE frameworks either heavily…

Machine Learning · Computer Science 2025-12-24 Sumin Park , Noseong Park

Model editing aims to efficiently alter the behavior of Large Language Models (LLMs) within a desired scope, while ensuring no adverse impact on other inputs. Recent years have witnessed various model editing methods been proposed. However,…

Computation and Language · Computer Science 2024-06-04 Renzhi Wang , Piji Li

In this paper, we introduce a novel dynamic expert selection framework for Mixture of Experts (MoE) models, aiming to enhance computational efficiency and model performance by adjusting the number of activated experts based on input…

Machine Learning · Computer Science 2024-03-13 Quzhe Huang , Zhenwei An , Nan Zhuang , Mingxu Tao , Chen Zhang , Yang Jin , Kun Xu , Kun Xu , Liwei Chen , Songfang Huang , Yansong Feng

Deep learning based semantic communication has achieved significant progress in wireless image transmission, but most existing schemes rely on fixed models and thus lack robustness to diverse image contents and dynamic channel conditions.…

Machine Learning · Computer Science 2026-04-06 Haowen Wan , Qianqian Yang

Multimodal large language models (MLLMs) have garnered widespread attention from researchers due to their remarkable understanding and generation capabilities in visual language tasks (e.g., visual question answering). However, the rapid…

Computer Vision and Pattern Recognition · Computer Science 2025-03-04 Tianyu Huai , Jie Zhou , Xingjiao Wu , Qin Chen , Qingchun Bai , Ze Zhou , Liang He

Despite the computational efficiency of MoE models, the excessive memory footprint and I/O overhead inherent in multi-expert architectures pose formidable challenges for real-time inference on resource-constrained edge platforms. While…

Machine Learning · Computer Science 2026-03-20 Yuegui Huang , Zhiyuan Fang , Weiqi Luo , Ruoyu Wu , Wuhui Chen , Zibin Zheng