English
Related papers

Related papers: Router-Tuning: A Simple and Effective Approach for…

200 papers

Early stopping based on the validation set performance is a popular approach to find the right balance between under- and overfitting in the context of supervised learning. However, in reinforcement learning, even for supervised…

Machine Learning · Computer Science 2023-03-20 Nicolai Dorka , Tim Welschehold , Wolfram Burgard

Mixture-of-Experts (MoE) architectures achieve parameter efficiency through conditional computation, yet contemporary designs suffer from two fundamental limitations: structural parameter isolation that causes catastrophic forgetting, and…

Machine Learning · Computer Science 2026-01-21 Yuxing Gan , Ziyu Lei

Despite their prevalence in deep-learning communities, over-parameterized models convey high demands of computational costs for proper training. This work studies the fine-grained, modular-level learning dynamics of over-parameterized…

When training a neural network for a desired task, one may prefer to adapt a pre-trained network rather than starting from randomly initialized weights. Adaptation can be useful in cases when training data is scarce, when a single learner…

Machine Learning · Computer Science 2020-08-03 Jeffrey O Zhang , Alexander Sax , Amir Zamir , Leonidas Guibas , Jitendra Malik

It is a common belief that training deep transformers from scratch requires large datasets. Consequently, for small datasets, people usually use shallow and simple additional layers on top of pre-trained models during fine-tuning. This work…

Computation and Language · Computer Science 2021-06-01 Peng Xu , Dhruv Kumar , Wei Yang , Wenjie Zi , Keyi Tang , Chenyang Huang , Jackie Chi Kit Cheung , Simon J. D. Prince , Yanshuai Cao

LoRA-MoE has emerged as an effective paradigm for parameter-efficient fine-tuning, combining the low training cost of LoRA with the increased adaptation capacity of Mixture-of-Experts (MoE). However, existing LoRA-MoE frameworks typically…

Machine Learning · Computer Science 2026-04-30 Weihang Li , Jianchun Liu , Hongli Xu

Mixture-of-Experts (MoE) has emerged as an effective approach to reduce the computational overhead of Transformer architectures by sparsely activating a subset of parameters for each token while preserving high model capacity. This paradigm…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Dohwan Ko , Jinyoung Park , Seoung Choi , Sanghyeok Lee , Seohyun Lee , Hyunwoo J. Kim

The development of large language models (LLMs) has expanded to multi-modal systems capable of processing text, images, and speech within a unified framework. Training these models demands significantly larger datasets and computational…

Computation and Language · Computer Science 2025-05-09 Weixin Liang , Lili Yu , Liang Luo , Srinivasan Iyer , Ning Dong , Chunting Zhou , Gargi Ghosh , Mike Lewis , Wen-tau Yih , Luke Zettlemoyer , Xi Victoria Lin

Mixup is a popular regularization technique for training deep neural networks that improves generalization and increases robustness to certain distribution shifts. It perturbs input training data in the direction of other randomly-chosen…

Machine Learning · Computer Science 2023-10-10 Kristjan Greenewald , Anming Gu , Mikhail Yurochkin , Justin Solomon , Edward Chien

The attention mechanism in its standard implementation contains extraneous rotational degrees of freedom that are carried through computation but do not affect model activations or outputs. We introduce a simple symmetry-breaking protocol…

Machine Learning · Computer Science 2026-02-13 Eva Silverstein , Daniel Kunin , Vasudev Shyam

Mixture-of-Experts (MoE) models have demonstrated exceptional performance in large-scale language models. Existing routers typically rely on non-differentiable Top-$k$+Softmax, limiting their performance and scalability. We argue that two…

Fine-tuning is a popular way of exploiting knowledge contained in a pre-trained convolutional network for a new visual recognition task. However, the orthogonal setting of transferring knowledge from a pretrained network to a visually…

Computer Vision and Pattern Recognition · Computer Science 2020-08-28 Amelie Royer , Christoph H. Lampert

Recent advances in large language models highlighted the excessive quadratic cost of self-attention. Despite the significant research efforts, subquadratic attention methods still suffer from inferior performance in practice. We hypothesize…

Machine Learning · Computer Science 2025-05-02 Piotr Piękos , Róbert Csordás , Jürgen Schmidhuber

Multimodal Deep Learning has garnered much interest, and transformers have triggered novel approaches, thanks to the cross-attention mechanism. Here we propose an approach to deal with two key existing challenges: the high computational…

Machine Learning · Computer Science 2021-10-20 Dhruv Agarwal , Tanay Agrawal , Laura M. Ferrari , François Bremond

We propose Tensor-Trained Low-Rank Adaptation Mixture of Experts (TT-LoRA MoE), a novel computational framework integrating Parameter-Efficient Fine-Tuning (PEFT) with sparse MoE routing to address scalability challenges in large model…

Machine Learning · Computer Science 2026-01-27 Pradip Kunwar , Minh N. Vu , Maanak Gupta , Mahmoud Abdelsalam , Manish Bhattarai

The Mixtures-of-Experts (MoE) model is a widespread distributed and integrated learning method for large language models (LLM), which is favored due to its ability to sparsify and expand models efficiently. However, the performance of MoE…

Machine Learning · Computer Science 2024-05-24 Jing Li , Zhijie Sun , Xuan He , Li Zeng , Yi Lin , Entong Li , Binfan Zheng , Rongqian Zhao , Xin Chen

Mixture-of-Experts (MoE) architectures have emerged as a leading paradigm for scaling large language models through sparse, routing-based computation. However, this design introduces a new attack surface: the routing mechanism that…

Cryptography and Security · Computer Science 2026-05-07 Zekun Fei , Zihao Wang , Weijie Liu , Ruiqi He , Jianing Geng , Zheli Liu , XiaoFeng Wang

Deep learning on an edge device requires energy efficient operation due to ever diminishing power budget. Intentional low quality data during the data acquisition for longer battery life, and natural noise from the low cost sensor degrade…

Machine Learning · Computer Science 2019-04-30 Taesik Na , Minah Lee , Burhan A. Mudassar , Priyabrata Saha , Jong Hwan Ko , Saibal Mukhopadhyay

Mixture-of-Experts (MoE) layers scale transformers by routing tokens to a sparse subset of feed-forward experts. Token-level routing, however, assigns an entire semantic spectrum to each expert, creating capacity bottlenecks, load-balancing…

Computation and Language · Computer Science 2025-10-07 Harshil Vejendla

As a foundational architecture of artificial intelligence models, Transformer has been recently adapted to spiking neural networks with promising performance across various tasks. However, existing spiking Transformer(ST)-based models…

Machine Learning · Computer Science 2026-01-06 Hongze Sun , Wuque Cai , Duo Chen , Quan Tang , Shifeng Mao , Jiayi He , Zhenxing Wang , Yan Cui , Dezhong Yao , Daqing Guo