English
Related papers

Related papers: SwitchHead: Accelerating Transformers with Mixture…

200 papers

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…

Sparse Mixture-of-Experts (MoE) models offer a powerful way to scale model size without increasing compute, as per-token FLOPs depend only on k active experts rather than the total pool of E experts. Yet, this asymmetry creates an MoE…

Machine Learning · Computer Science 2026-05-15 Linghao Jin , Chufan Shi , Huijuan Wang , Nuan Wen , Zhengzhong Liu , Eric Xing , Xuezhe Ma

Mixture-of-Experts (MoE) scales language models efficiently through sparse expert activation, and its dynamic variant further reduces computation by adjusting the activated experts in an input-dependent manner. Existing dynamic MoE methods…

Recently, the Transformer machine translation system has shown strong results by stacking attention layers on both the source and target-language sides. But the inference of this model is slow due to the heavy use of dot-product attention…

Computation and Language · Computer Science 2019-06-27 Tong Xiao , Yinqiao Li , Jingbo Zhu , Zhengtao Yu , Tongran Liu

Mixture-of-Experts (MoE) is now the dominant architecture for frontier language models, yet it requires all expert parameters to be loaded in memory, making it less preferable for memory-constrained deployment. Existing compression methods…

Computation and Language · Computer Science 2026-05-28 Junhyuck Kim , Jihun Yun , Haechan Kim , Gyeongman Kim , Joonghyun Bae , Jaewoong Cho

The attention mechanism has been the core component in modern transformer architectures. However, the computation of standard full attention scales quadratically with the sequence length, serving as a major bottleneck in long-context…

Computation and Language · Computer Science 2026-04-28 Yusheng Zhao , Hourun Li , Bohan Wu , Yichun Yin , Lifeng Shang , Jingyang Yuan , Meng Zhang , Ming Zhang

Mixture of Experts (MoEs) have become a central component of many state-of-the-art open-source and proprietary large language models. Despite their widespread adoption, it remains unclear how close existing MoE architectures are to optimal…

Large language models have transformed many applications but remain expensive to train. Sparse Mixture of Experts (MoE) addresses this through conditional computation, with Expert Parallel (EP) as the standard distributed training method.…

Machine Learning · Computer Science 2026-02-05 Chenwei Cui , Rockwell Jackson , Benjamin Joseph Herrera , Ana María Tárano , Hannah Kerner

Sliding-window attention offers a hardware-efficient solution to the memory and throughput challenges of Large Language Models (LLMs) in long-context scenarios. Existing methods typically employ a single window length across all attention…

Continual learning can empower vision-language models to continuously acquire new knowledge, without the need for access to the entire historical dataset. However, mitigating the performance degradation in large-scale models is non-trivial…

Computer Vision and Pattern Recognition · Computer Science 2024-06-04 Jiazuo Yu , Yunzhi Zhuge , Lu Zhang , Ping Hu , Dong Wang , Huchuan Lu , You He

Mixture-of-experts (MoE) is gaining increasing attention due to its unique properties and remarkable performance, especially for language tasks. By sparsely activating a subset of parameters for each token, MoE architecture could increase…

Computation and Language · Computer Science 2025-06-24 Ka Man Lo , Zeyu Huang , Zihan Qiu , Zili Wang , Jie Fu

Transformer-based models have been achieving state-of-the-art results in several fields of Natural Language Processing. However, its direct application to speech tasks is not trivial. The nature of this sequences carries problems such as…

Computation and Language · Computer Science 2022-05-17 Gerard Sant , Gerard I. Gállego , Belen Alastruey , Marta R. Costa-Jussà

All-MLP architectures have attracted increasing interest as an alternative to attention-based models. In NLP, recent work like gMLP shows that all-MLPs can match Transformers in language modeling, but still lag behind in downstream tasks.…

Computation and Language · Computer Science 2022-06-02 Ping Yu , Mikel Artetxe , Myle Ott , Sam Shleifer , Hongyu Gong , Ves Stoyanov , Xian Li

Large language models (LLMs) such as GPTs and Mixtral-8x7B have revolutionized machine intelligence due to their exceptional abilities in generic ML tasks. Transiting LLMs from datacenters to edge devices brings benefits like better privacy…

Machine Learning · Computer Science 2025-03-10 Rongjie Yi , Liwei Guo , Shiyun Wei , Ao Zhou , Shangguang Wang , Mengwei Xu

Emerging expert-specialized Mixture-of-Experts (MoE) architectures, such as DeepSeek-MoE, deliver strong model quality through fine-grained expert segmentation and large top-k routing. However, their scalability is limited by substantial…

Machine Learning · Computer Science 2025-08-20 Yueming Yuan , Ahan Gupta , Jianping Li , Sajal Dash , Feiyi Wang , Minjia Zhang

Mixture-of-Experts (MoE) models mostly use a router to assign tokens to specific expert modules, activating only partial parameters and often outperforming dense models. We argue that the separation between the router's decision-making and…

Computation and Language · Computer Science 2025-06-02 Ang Lv , Ruobing Xie , Yining Qian , Songhao Wu , Xingwu Sun , Zhanhui Kang , Di Wang , Rui Yan

Mixture-of-Experts (MoE), a conditional computation architecture, achieved promising performance by scaling local module (i.e. feed-forward network) of transformer. However, scaling the cross-token module (i.e. self-attention) is…

Machine Learning · Computer Science 2022-01-17 Yuxuan Lou , Fuzhao Xue , Zangwei Zheng , Yang You

Mixture-of-Experts (MoE) has emerged as a prominent architecture for scaling model size while maintaining computational efficiency. In MoE, each token in the input sequence activates a different subset of experts determined by a routing…

Computation and Language · Computer Science 2024-11-05 Chufan Shi , Cheng Yang , Xinyu Zhu , Jiahao Wang , Taiqiang Wu , Siheng Li , Deng Cai , Yujiu Yang , Yu Meng

As the Mix-of-Experts (MoE) architecture increases the number of parameters in large models, there is an even greater need for model quantization. However, existing quantization methods overlook the expert dynamics of MoE across multiple…

Machine Learning · Computer Science 2026-01-12 Zihao Zheng , Xiuping Cui , Size Zheng , Maoliang Li , Jiayu Chen , Yun Liang , Xiang Chen

Mixture of Experts (MoE) models enhance neural network scalability by dynamically selecting relevant experts per input token, enabling larger model sizes while maintaining manageable computation costs. However, efficient training of…