English
Related papers

Related papers: Dynamic Mixture-of-Experts for Visual Autoregressi…

200 papers

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

The Mixture-of-Experts (MoE) approach has demonstrated outstanding scalability in multi-task learning including low-level upstream tasks such as concurrent removal of multiple adverse weather effects. However, the conventional MoE…

Computer Vision and Pattern Recognition · Computer Science 2023-12-29 Rongyu Zhang , Yulin Luo , Jiaming Liu , Huanrui Yang , Zhen Dong , Denis Gudovskiy , Tomoyuki Okuno , Yohei Nakata , Kurt Keutzer , Yuan Du , Shanghang Zhang

By routing input tokens to only a few split experts, Sparse Mixture-of-Experts has enabled efficient training of large language models. Recent findings suggest that fixing the routers can achieve competitive performance by alleviating the…

The vector autoregressive (VAR) model has been used to describe the dependence within and across multiple time series. This is a model for stationary time series which can be extended to allow the presence of a deterministic trend in each…

Methodology · Statistics 2025-10-14 Xixi Li , Jingsong Yuan

We investigate the fundamental limits of transformer-based foundation models, extending our analysis to include Visual Autoregressive (VAR) transformers. VAR represents a big step toward generating images using a novel, scalable,…

Machine Learning · Computer Science 2025-02-11 Yifang Chen , Xiaoyu Li , Yingyu Liang , Zhenmei Shi , Zhao Song

Transformer architecture search (TAS) discovers optimal vision transformer (ViT) architectures automatically, reducing human effort to manually design ViTs. However, existing TAS methods suffer from the feature collapse problem, where…

Computer Vision and Pattern Recognition · Computer Science 2026-05-11 Jeimin Jeon , Hyunju Lee , Bumsub Ham

Mixture-of-Experts (MoE) models have shown promising potential for parameter-efficient scaling across domains. However, their application to image classification remains limited, often requiring billion-scale datasets to be competitive. In…

Computer Vision and Pattern Recognition · Computer Science 2025-10-27 Mathurin Videau , Alessandro Leite , Marc Schoenauer , Olivier Teytaud

Recent progress in deep learning has been driven by increasingly large-scale models, but the resulting computational cost has become a critical bottleneck. Sparse Mixture of Experts (MoE) offers an effective solution by activating only a…

Computer Vision and Pattern Recognition · Computer Science 2026-04-24 Masahiro Kada , Ryota Yoshihashi , Satoshi Ikehata , Rei Kawakami , Ikuro Sato

Mixture-of-experts (MoE) architectures have expanded from language modeling to automatic speech recognition (ASR). Traditional MoE methods, such as the Switch Transformer, route experts independently within each layer. Our analysis reveals…

Computation and Language · Computer Science 2025-11-06 Zijin Gu , Tatiana Likhomanenko , Navdeep Jaitly

We propose a monocular depth estimation method based on visual autoregressive (VAR) priors, offering an alternative to diffusion-based approaches. Our method adapts a large-scale text-to-image VAR model and introduces a scale-wise…

Computer Vision and Pattern Recognition · Computer Science 2025-12-30 Amir El-Ghoussani , André Kaup , Nassir Navab , Gustavo Carneiro , Vasileios Belagiannis

Understanding the expressive ability of a specific model is essential for grasping its capacity limitations. Recently, several studies have established circuit complexity bounds for Transformer architecture. Besides, the Visual…

Machine Learning · Statistics 2025-01-09 Yekun Ke , Xiaoyu Li , Yingyu Liang , Zhenmei Shi , Zhao Song

We propose a novel mixture-of-experts class to optimize computer vision models in accordance with data transfer limitations at test time. Our approach postulates that the minimum acceptable amount of data allowing for highly-accurate…

Machine Learning · Computer Science 2020-09-02 Alhabib Abbas , Yiannis Andreopoulos

Mixture-of-Experts (MoE) models scale capacity via sparse activation but stress memory and bandwidth. Offloading alleviates GPU memory by fetching experts on demand, yet token-level routing causes irregular transfers that make inference…

Machine Learning · Computer Science 2025-12-22 Zhenyu Liu , Yunzhen Liu , Zehao Fan , Garrett Gagnon , Yayue Hou , Nan Wu , Yangwook Kang , Liu Liu

Mixture-of-Experts (MoE) models are a promising way to scale up model capacity without significantly increasing computational cost. A key component of MoEs is the router, which decides which subset of parameters (experts) process which…

Computer Vision and Pattern Recognition · Computer Science 2024-04-22 Tianlin Liu , Mathieu Blondel , Carlos Riquelme , Joan Puigcerver

Autoregressive (AR) modeling has achieved remarkable success in natural language processing by enabling models to generate text with coherence and contextual understanding through next token prediction. Recently, in image generation, VAR…

Computer Vision and Pattern Recognition · Computer Science 2024-12-20 Sucheng Ren , Qihang Yu , Ju He , Xiaohui Shen , Alan Yuille , Liang-Chieh Chen

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.…

Computation and Language · Computer Science 2022-10-13 Zewen Chi , Li Dong , Shaohan Huang , Damai Dai , Shuming Ma , Barun Patra , Saksham Singhal , Payal Bajaj , Xia Song , Xian-Ling Mao , Heyan Huang , Furu Wei

The Mixture of Experts (MoE) architecture has excelled in Large Vision-Language Models (LVLMs), yet its potential in real-time open-vocabulary object detectors, which also leverage large-scale vision-language datasets but smaller models,…

Computer Vision and Pattern Recognition · Computer Science 2025-07-24 Yehao Lu , Minghe Weng , Zekang Xiao , Rui Jiang , Wei Su , Guangcong Zheng , Ping Lu , Xi Li

Recent advances in dynamic scene reconstruction have significantly benefited from 3D Gaussian Splatting, yet existing methods show inconsistent performance across diverse scenes, indicating no single approach effectively handles all dynamic…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 In-Hwan Jin , Hyeongju Mun , Joonsoo Kim , Kugjin Yun , Kyeongbo Kong

Mixture-of-Experts models, now popular for scaling capacity at fixed inference speed, switch experts at nearly every token. Once a model outgrows available GPU memory, this churn can render optimizations like offloading and pre-fetching…

Machine Learning · Computer Science 2026-04-23 Zeyu Shen , Peter Henderson

The feedforward (FFW) layers in standard transformer architectures incur a linear increase in computational costs and activation memory as the hidden layer width grows. Sparse mixture-of-experts (MoE) architectures have emerged as a viable…

Machine Learning · Computer Science 2024-07-08 Xu Owen He
‹ Prev 1 3 4 5 6 7 10 Next ›