English
Related papers

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

200 papers

Long-tailed visual recognition is challenging not only due to class imbalance but also because of varying classification difficulty across categories. Simply reweighting classes by frequency often overlooks those that are intrinsically hard…

Computer Vision and Pattern Recognition · Computer Science 2025-08-28 Xiaolei Wei , Yi Ouyang , Haibo Ye

With a growing number of robots being deployed across diverse applications, robust multimodal anomaly detection becomes increasingly important. In robotic manipulation, failures typically arise from (1) robot-driven anomalies due to an…

Robotics · Computer Science 2025-06-25 Christoph Willibald , Daniel Sliwowski , Dongheui Lee

Thanks to High Dynamic Range (HDR) imaging methods, the scope of photography has seen profound changes recently. To be more specific, such methods try to reconstruct the lost luminosity of the real world caused by the limitation of regular…

Computer Vision and Pattern Recognition · Computer Science 2024-04-23 Ali Reza Omrani , Davide Moroni

In this paper, we propose an end-to-end lifelong learning mixture of experts. Each expert is implemented by a Variational Autoencoder (VAE). The experts in the mixture system are jointly trained by maximizing a mixture of individual…

Machine Learning · Computer Science 2021-07-13 Fei Ye , Adrian G. Bors

The raster-ordered image token sequence exhibits a significant Euclidean distance between index-adjacent tokens at line breaks, making it unsuitable for autoregressive generation. To address this issue, this paper proposes Direction-Aware…

Computer Vision and Pattern Recognition · Computer Science 2025-04-17 Yijia Xu , Jianzhong Ju , Jian Luan , Jinshi Cui

Sparsely-activated Mixture-of-experts (MoE) models allow the number of parameters to greatly increase while keeping the amount of computation for a given token or a given sample unchanged. However, a poor expert routing strategy (e.g. one…

Machine Learning · Computer Science 2022-10-17 Yanqi Zhou , Tao Lei , Hanxiao Liu , Nan Du , Yanping Huang , Vincent Zhao , Andrew Dai , Zhifeng Chen , Quoc Le , James Laudon

Multimodal large language models (MLLMs) require a nuanced interpretation of complex image information, typically leveraging a vision encoder to perceive various visual scenarios. However, relying solely on a single vision encoder to handle…

Computer Vision and Pattern Recognition · Computer Science 2025-06-02 Xin He , Xumeng Han , Longhui Wei , Lingxi Xie , Qi Tian

Recent advances in diffusion models have brought remarkable visual fidelity to instruction-guided image editing. However, their global denoising process inherently entangles the edited region with the entire image context, leading to…

Computer Vision and Pattern Recognition · Computer Science 2026-02-09 Qingyang Mao , Qi Cai , Yehao Li , Yingwei Pan , Mingyue Cheng , Ting Yao , Qi Liu , Tao Mei

Implicit neural representations (INRs) have proven effective in various tasks including image, shape, audio, and video reconstruction. These INRs typically learn the implicit field from sampled input points. This is often done using a…

Computer Vision and Pattern Recognition · Computer Science 2024-10-30 Yizhak Ben-Shabat , Chamin Hewa Koneputugodage , Sameera Ramasinghe , Stephen Gould

Mixture-of-Experts (MoE) architectures have emerged as a cornerstone of modern AI systems. In particular, MoEs route inputs dynamically to specialized experts whose outputs are aggregated through weighted summation. Despite their widespread…

Machine Learning · Computer Science 2025-10-09 Fangshuo Liao , Anastasios Kyrillidis

Mixture-of-experts (MoE) models enable scalable transformer architectures by activating only a subset of experts per token. Recent evidence suggests that performance improves with increasingly granular experts, i.e., many small experts…

Machine Learning · Computer Science 2026-05-07 Klaus-Rudolf Kladny , Maximilian Mordig , Bernhard Schölkopf , Michael Muehlebach

Vision Transformer (ViT) is emerging as the state-of-the-art architecture for image recognition. While recent studies suggest that ViTs are more robust than their convolutional counterparts, our experiments find that ViTs trained on…

Computer Vision and Pattern Recognition · Computer Science 2022-04-05 Chengzhi Mao , Lu Jiang , Mostafa Dehghani , Carl Vondrick , Rahul Sukthankar , Irfan Essa

Recently, transformer networks have outperformed traditional deep neural networks in natural language processing and show a large potential in many computer vision tasks compared to convolutional backbones. In the original transformer,…

Computer Vision and Pattern Recognition · Computer Science 2023-03-03 Chen-Chou Lo , Patrick Vandewalle

Mixture-of-experts based acoustic models with dynamic routing mechanisms have proved promising results for speech recognition. The design principle of router architecture is important for the large model capacity and high computational…

Audio and Speech Processing · Electrical Eng. & Systems 2021-11-24 Zhao You , Shulin Feng , Dan Su , Dong Yu

Fine-tuning pre-trained generative models with Reinforcement Learning (RL) has emerged as an effective approach for aligning outputs more closely with nuanced human preferences. In this paper, we investigate the application of Group…

Computer Vision and Pattern Recognition · Computer Science 2025-07-01 Matteo Gallici , Haitz Sáez de Ocáriz Borde

Sparsely activated models (SAMs), such as Mixture-of-Experts (MoE), can easily scale to have outrageously large amounts of parameters without significant increase in computational cost. However, SAMs are reported to be parameter inefficient…

Computation and Language · Computer Science 2022-02-07 Simiao Zuo , Xiaodong Liu , Jian Jiao , Young Jin Kim , Hany Hassan , Ruofei Zhang , Tuo Zhao , Jianfeng Gao

Mixture-of-Experts (MoE) has emerged as a promising paradigm for efficiently scaling large language models without a proportional increase in computational cost. However, the standard training strategy of Top-K router prevents MoE models…

Computation and Language · Computer Science 2025-10-01 Yaoxiang Wang , Qingguo Hu , Yucheng Ding , Ruizhe Wang , Yeyun Gong , Jian Jiao , Yelong Shen , Peng Cheng , Jinsong Su

Essential to visual generation is efficient modeling of visual data priors. Conventional next-token prediction methods define the process as learning the conditional probability distribution of successive tokens. Recently, next-scale…

Computer Vision and Pattern Recognition · Computer Science 2026-02-03 Jinhua Zhang , Wei Long , Minghao Han , Weiyi You , Shuhang Gu

Sparsely activated Mixture-of-Experts (MoE) models effectively increase the number of parameters while maintaining consistent computational costs per token. However, vanilla MoE models often suffer from limited diversity and specialization…

Machine Learning · Computer Science 2025-07-11 Lei Kang , Jia Li , Mi Tian , Hua Huang

VAR is a new generation paradigm that employs 'next-scale prediction' as opposed to 'next-token prediction'. This innovative transformation enables auto-regressive (AR) transformers to rapidly learn visual distributions and achieve robust…

Computer Vision and Pattern Recognition · Computer Science 2024-08-05 Qian Zhang , Xiangzi Dai , Ninghua Yang , Xiang An , Ziyong Feng , Xingyu Ren