English
Related papers

Related papers: Drop-Upcycling: Training Sparse Mixture of Experts…

200 papers

Mixture-of-Experts (MoE) models are crucial for scaling model capacity while controlling inference costs. While integrating MoE into multimodal models like CLIP improves performance, training these models is notoriously challenging and…

Computer Vision and Pattern Recognition · Computer Science 2025-05-27 Xinze Wang , Chen Chen , Yinfei Yang , Hong-You Chen , Bowen Zhang , Aditya Pal , Xiangxin Zhu , Xianzhi Du

Sparse Upcycling provides an efficient way to initialize a Mixture-of-Experts (MoE) model from pretrained dense weights instead of training from scratch. However, since all experts start from identical weights and the router is randomly…

Computer Vision and Pattern Recognition · Computer Science 2026-04-20 Sanghyeok Chu , Pyunghwan Ahn , Gwangmo Song , SeungHwan Kim , Honglak Lee , Bohyung Han

Mixture-of-Experts (MoE) has become the dominant architecture for scaling large language models: frontier models routinely decouple total parameters from per-token computation through sparse expert routing. Scaling laws show that under…

Machine Learning · Computer Science 2026-05-12 Chaitanya Dwivedi , Binxuan Huang , Himanshu Gupta , Pratik Jayarao , Neeraj Varshney , Bing Yin

Upcycling pre-trained dense language models into sparse mixture-of-experts (MoE) models is an efficient approach to increase the model capacity of already trained models. However, optimal techniques for upcycling at scale remain unclear. In…

Computation and Language · Computer Science 2025-06-17 Ethan He , Abhinav Khattar , Ryan Prenger , Vijay Korthikanti , Zijie Yan , Tong Liu , Shiqing Fan , Ashwath Aithal , Mohammad Shoeybi , Bryan Catanzaro

The Mixture-of-Experts (MoE) models have gained significant attention in deep learning due to their dynamic resource allocation and superior performance across diverse tasks. However, efficiently training these models remains challenging.…

Computation and Language · Computer Science 2025-09-03 Junfeng Ran , Guangxiang Zhao , Yuhan Wu , Dawei Zhu , Longyun Wu , Yikai Zhao , Tong Yang , Lin Sun , Xiangzheng Zhang , Sujian Li

Mixture-of-Experts (MoE) shines brightly in large language models (LLMs) and demonstrates outstanding performance in plentiful natural language processing tasks. However, existing methods transforming LLMs from dense to MoE face significant…

Computation and Language · Computer Science 2024-10-04 Tingfeng Hui , Zhenyu Zhang , Shuohuan Wang , Yu Sun , Hua Wu , Sen Su

Mixture-of-Experts (MoE) models enable scalable performance by activating large parameter sets sparsely, minimizing computational overhead. To mitigate the prohibitive cost of training MoEs from scratch, recent work employs upcycling,…

Machine Learning · Computer Science 2025-11-13 Qi Wang , Hanyang Peng , Yue Yu

Modern deep learning is increasingly characterized by the use of open-weight foundation models that can be fine-tuned on specialized datasets. This has led to a proliferation of expert models and adapters, often shared via platforms like…

Machine Learning · Computer Science 2025-06-18 Stefan Horoi , Guy Wolf , Eugene Belilovsky , Gintare Karolina Dziugaite

Small, highly trained, open-source large language models are widely used due to their inference efficiency, but further improving their quality remains a challenge. Sparse upcycling is a promising approach that transforms a pretrained dense…

Machine Learning · Computer Science 2024-11-15 Sasha Doubov , Nikhil Sardana , Vitaliy Chiley

Upcycled Mixture-of-Experts (MoE) models have shown great potential in various tasks by converting the original Feed-Forward Network (FFN) layers in pre-trained dense models into MoE layers. However, these models still suffer from…

Machine Learning · Computer Science 2025-03-04 Yongqi Huang , Peng Ye , Chenyu Huang , Jianjian Cao , Lin Zhang , Baopu Li , Gang Yu , Tao Chen

Mixture of Experts (MoE) pretraining is more scalable than dense Transformer pretraining, because MoEs learn to route inputs to a sparse set of their feedforward parameters. However, this means that MoEs only receive a sparse backward…

Machine Learning · Computer Science 2025-11-05 Ashwinee Panda , Vatsal Baherwani , Zain Sarwar , Benjamin Therien , Sambit Sahu , Tom Goldstein , Supriyo Chakraborty

Pretraining large language models (LLMs) is resource-intensive, often requiring months of training time even with high-end GPU clusters. There are two approaches of mitigating such computational demands: reusing smaller models to train…

Machine Learning · Computer Science 2025-06-17 Seng Pei Liew , Takuya Kato , Sho Takase

The Mixture of Experts (MoE) framework has become a popular architecture for large language models due to its superior performance over dense models. However, training MoEs from scratch in a large-scale regime is prohibitively expensive.…

Large Language Models (LLMs) have achieved remarkable performance on a wide range of specialized tasks, exhibiting strong problem-solving capabilities. However, training these models is prohibitively expensive, and they often lack…

Machine Learning · Computer Science 2026-04-01 Eros Fanì , Oğuzhan Ersoy

As the training of giant dense models hits the boundary on the availability and capability of the hardware resources today, Mixture-of-Experts (MoE) models become one of the most promising model architectures due to their significant…

The Mixture of Experts (MoE) models are an emerging class of sparsely activated deep learning models that have sublinear compute costs with respect to their parameters. In contrast with dense models, the sparse architecture of MoE offers…

Mixture-of-experts (MoE) is becoming popular due to its success in improving the model quality, especially in Transformers. By routing tokens with a sparse gate to a few experts (i.e., a small pieces of the full model), MoE can easily…

Machine Learning · Computer Science 2022-10-11 Xiaonan Nie , Xupeng Miao , Shijie Cao , Lingxiao Ma , Qibin Liu , Jilong Xue , Youshan Miao , Yi Liu , Zhi Yang , Bin Cui

Scaling large language models (LLMs) significantly improves performance but comes with prohibitive computational costs. Mixture-of-Experts (MoE) models offer an efficient alternative, increasing capacity without a proportional rise in…

Machine Learning · Computer Science 2024-12-16 Aditya Vavre , Ethan He , Dennis Liu , Zijie Yan , June Yang , Nima Tajbakhsh , Ashwath Aithal

Efficiency, specialization, and adaptability to new data distributions are qualities that are hard to combine in current Large Language Models. The Mixture of Experts (MoE) architecture has been the focus of significant research because its…

Computation and Language · Computer Science 2024-08-29 Nikolas Gritsch , Qizhen Zhang , Acyr Locatelli , Sara Hooker , Ahmet Üstün

Upcycling pre-trained dense models into sparse Mixture-of-Experts (MoEs) efficiently increases model capacity but often suffers from poor expert specialization due to naive weight replication. Our analysis reveals that upcycled MoEs, even…

Machine Learning · Computer Science 2025-10-02 Leyla Mirvakhabova , Babak Ehteshami Bejnordi , Gaurav Kumar , Hanxue Liang , Wanru Zhao , Paul Whatmough
‹ Prev 1 2 3 10 Next ›