English
Related papers

Related papers: Split-on-Share: Mixture of Sparse Experts for Task…

200 papers

Recent successes suggest that parameter-efficient fine-tuning of foundation models as the state-of-the-art method for transfer learning in vision, replacing the rich literature of alternatives such as meta-learning. In trying to harness the…

Computer Vision and Pattern Recognition · Computer Science 2024-07-02 Shengzhuang Chen , Jihoon Tack , Yunqiao Yang , Yee Whye Teh , Jonathan Richard Schwarz , Ying Wei

In-context learning, the ability to adapt based on a few examples in the input prompt, is a ubiquitous feature of large language models (LLMs). However, as LLMs' in-context learning abilities continue to improve, understanding this…

Machine Learning · Computer Science 2024-10-03 Can Demircan , Tankred Saanum , Akshay K. Jagadish , Marcel Binz , Eric Schulz

Continual Learning requires a model to learn multiple tasks in sequence while maintaining both stability:preserving knowledge from previously learned tasks, and plasticity:effectively learning new tasks. Gradient projection has emerged as…

Machine Learning · Computer Science 2025-06-12 Haomiao Qiu , Miao Zhang , Ziyue Qiao , Weili Guan , Min Zhang , Liqiang Nie

Although many efforts have been made, it is still a challenge to balance the training budget, downstream performance, and the general capabilities of the LLMs in many applications. Training the whole model for downstream tasks is expensive,…

Machine Learning · Computer Science 2025-01-29 Jiayi Han , Liang Du , Hongwei Du , Xiangguo Zhou , Yiwen Wu , Weibo Zheng , Donghong Han

Large Language Model (LLM)-based agents significantly extend the utility of LLMs by interacting with dynamic environments. However, enabling agents to continually learn new tasks without catastrophic forgetting remains a critical challenge,…

Computation and Language · Computer Science 2026-04-14 Zheng Wu , Xingyu Lou , Xinbei Ma , Yansi Li , Weiwen Liu , Weinan Zhang , Jun Wang , Zhuosheng Zhang

Sparse Mixture of Experts (SMoE) enables efficient training of large language models by routing input tokens to a select number of experts. However, training SMoE remains challenging due to the issue of representation collapse. Recent…

Computation and Language · Computer Science 2025-04-01 Giang Do , Hung Le , Truyen Tran

Large language models (LLMs) demonstrate strong task-specific capabilities through fine-tuning, but merging multiple fine-tuned models often leads to degraded performance due to overlapping instruction-following components. Task Arithmetic…

Computation and Language · Computer Science 2025-02-28 Yan-Lun Chen , Yi-Ru Wei , Chia-Yi Hsu , Chia-Mu Yu , Chun-Ying Huang , Ying-Dar Lin , Yu-Sung Wu , Wei-Bin Lee

Mixture-of-Experts (MoE) architectures have become the dominant choice for scaling Large Language Models (LLMs), activating only a subset of parameters per token. While MoE architectures are primarily adopted for computational efficiency,…

Computation and Language · Computer Science 2026-05-19 Jeremy Herbst , Stefan Wermter , Jae Hee Lee

Continual learning has emerged as an increasingly important challenge across various tasks, including Spoken Language Understanding (SLU). In SLU, its objective is to effectively handle the emergence of new concepts and evolving…

Computation and Language · Computer Science 2024-02-19 Muqiao Yang , Xiang Li , Umberto Cappellazzo , Shinji Watanabe , Bhiksha Raj

Mixture of Experts (MoE) has become a key architectural paradigm for efficiently scaling Large Language Models (LLMs) by selectively activating a subset of parameters for each input token. However, standard MoE architectures face…

Machine Learning · Computer Science 2025-05-27 Zehua Liu , Han Wu , Ruifeng She , Xiaojin Fu , Xiongwei Han , Tao Zhong , Mingxuan Yuan

Continual learning enables large language models to adapt to evolving tasks without retraining from scratch, yet catastrophic forgetting remains a central obstacle. Among continual learning methods, regularization-based approaches are…

Machine Learning · Computer Science 2026-05-26 Mingxu Zhang , Yuhan Li , Lujundong Li , Dazhong Shen , Hui Xiong , Ying Sun

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

Parameter-efficient fine-tuning (PEFT) has emerged as an effective method for adapting pre-trained language models to various tasks efficiently. Recently, there has been a growing interest in transferring knowledge from one or multiple…

Computation and Language · Computer Science 2024-06-07 Zhisheng Lin , Han Fu , Chenghao Liu , Zhuo Li , Jianling Sun

Adapting large pretrained models to new tasks efficiently and continually is crucial for real-world deployment but remains challenging due to catastrophic forgetting and the high cost of retraining. While parameter-efficient tuning methods…

Machine Learning · Computer Science 2026-02-06 Prakhar Kaushik , Ankit Vaidya , Shravan Chaudhari , Rama Chellappa , Alan Yuille

Sparse expert models are a thirty-year old concept re-emerging as a popular architecture in deep learning. This class of architecture encompasses Mixture-of-Experts, Switch Transformers, Routing Networks, BASE layers, and others, all with…

Machine Learning · Computer Science 2022-09-07 William Fedus , Jeff Dean , Barret Zoph

It's challenging to balance the networks stability and plasticity in continual learning scenarios, considering stability suffers from the update of model and plasticity benefits from it. Existing works usually focus more on the stability…

Computer Vision and Pattern Recognition · Computer Science 2023-12-13 Yi Sun , Xin Xu , Jian Li , Guanglei Xie , Yifei Shi , Qiang Fang

With increasing applications in areas such as biomedical information extraction pipelines and social media analytics, Named Entity Recognition (NER) has become an indispensable tool for knowledge extraction. However, with the gradual shift…

Computation and Language · Computer Science 2022-06-30 Supriti Vijay , Aman Priyanshu

One notable weakness of current machine learning algorithms is the poor ability of models to solve new problems without forgetting previously acquired knowledge. The Continual Learning paradigm has emerged as a protocol to systematically…

Machine Learning · Computer Science 2022-11-16 Heinke Hihn , Daniel A. Braun

Large-scale pre-training of deep models, followed by fine-tuning them, has become the cornerstone of natural language processing (NLP). The prevalence of data coupled with computational resources has led to large models with a considerable…

Computation and Language · Computer Science 2025-03-17 Rachel S. Y. Teo , Tan M. Nguyen

Large Language Models (LLMs) hold immense potential to generate synthetic data of high quality and utility, which has numerous applications from downstream model training to practical data utilisation. However, contemporary models, despite…

Computation and Language · Computer Science 2023-08-21 Charles O'Neill , Yuan-Sen Ting , Ioana Ciuca , Jack Miller , Thang Bui