English
Related papers

Related papers: Dense vs Sparse Pretraining at Tiny Scale: Active-…

200 papers

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

Masked auto-encoder pre-training has emerged as a prevalent technique for initializing and enhancing dense retrieval systems. It generally utilizes additional Transformer decoder blocks to provide sustainable supervision signals and…

Information Retrieval · Computer Science 2024-04-23 Guangyuan Ma , Xing Wu , Zijia Lin , Songlin Hu

Sparse autoencoders (SAEs) are a useful tool for uncovering human-interpretable features in the activations of large language models (LLMs). While some expect SAEs to find the true underlying features used by a model, our research shows…

Machine Learning · Computer Science 2025-01-31 Gonçalo Paulo , Nora Belrose

Parameter Efficient Tuning has been an prominent approach to adapt the Large Language Model to downstream tasks. Most previous works considers adding the dense trainable parameters, where all parameters are used to adapt certain task. We…

Computation and Language · Computer Science 2023-11-16 Yun Zhu , Nevan Wichers , Chu-Cheng Lin , Xinyi Wang , Tianlong Chen , Lei Shu , Han Lu , Canoee Liu , Liangchen Luo , Jindong Chen , Lei Meng

Large multimodal Mixture-of-Experts (MoEs) effectively scale the model size to boost performance while maintaining fixed active parameters. However, previous works primarily utilized full-precision experts during sparse up-cycling. Despite…

Computer Vision and Pattern Recognition · Computer Science 2026-01-08 Hongyu Wang , Jiayu Xu , Ruiping Wang , Yan Feng , Yitao Zhai , Peng Pei , Xunliang Cai , Xilin Chen

An increasing number of LLMs employ Mixture-of-Experts (MoE) architectures where the feed-forward layer is replaced by a pool of experts and each token only activates a small subset of them. During autoregressive generation, these models…

Machine Learning · Computer Science 2025-11-05 Costin-Andrei Oncescu , Qingyang Wu , Wai Tong Chung , Robert Wu , Bryan Gopal , Junxiong Wang , Tri Dao , Ben Athiwaratkun

Large language models (LLMs) with the Mixture-of-Experts (MoE) architecture achieve high cost-efficiency by selectively activating a subset of the parameters. Despite the inference efficiency of MoE LLMs, the training of extensive experts…

Computation and Language · Computer Science 2025-06-12 Yuchen Feng , Bowen Shen , Naibin Gu , Jiaxuan Zhao , Peng Fu , Zheng Lin , Weiping Wang

Previous multi-task dense prediction methods based on the Mixture of Experts (MoE) have received great performance but they neglect the importance of explicitly modeling the global relations among all tasks. In this paper, we present a…

Computer Vision and Pattern Recognition · Computer Science 2024-05-28 Yuqi Yang , Peng-Tao Jiang , Qibin Hou , Hao Zhang , Jinwei Chen , Bo Li

Scaling model parameters improves model quality at the price of high computation overhead. Sparsely activated models, usually in the form of Mixture of Experts (MoE) architecture, have sub-linear scaling of computation cost with model size,…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-04-30 Jiamin Li , Yimin Jiang , Yibo Zhu , Cong Wang , Hong Xu

Mixture-of-Experts (MoE) has gained increasing popularity as a promising framework for scaling up large language models (LLMs). However, training MoE from scratch in a large-scale setting still suffers from data-hungry and instability…

Computation and Language · Computer Science 2024-06-25 Tong Zhu , Xiaoye Qu , Daize Dong , Jiacheng Ruan , Jingqi Tong , Conghui He , Yu Cheng

While Dense Retrieval Models (DRMs) have advanced Information Retrieval (IR), one limitation of these neural models is their narrow generalizability and robustness. To cope with this issue, one can leverage the Mixture-of-Experts (MoE)…

Information Retrieval · Computer Science 2024-12-17 Effrosyni Sokli , Pranav Kasela , Georgios Peikos , Gabriella Pasi

The sparse Mixture-of-Experts (MoE) architecture is increasingly favored for scaling Large Language Models (LLMs) efficiently, but it depends on heterogeneous compute and memory resources. These factors jointly affect system Cost, Accuracy,…

The sparse Mixture-of-Experts (MoE) architecture is increasingly favored for scaling Large Language Models (LLMs) efficiently, but it depends on heterogeneous compute and memory resources. These factors jointly affect system Cost, Accuracy,…

Mixture-of-Experts (MoE) models have recently demonstrated exceptional performance across a diverse range of applications. The principle of sparse activation in MoE models facilitates an offloading strategy, wherein active experts are…

Computation and Language · Computer Science 2025-10-15 Yushu Zhao , Yubin Qin , Yang Wang , Xiaolong Yang , Huiming Han , Shaojun Wei , Yang Hu , Shouyi Yin

The sparsely gated mixture of experts (MoE) architecture sends different inputs to different subnetworks, i.e., experts, through trainable routers. MoE reduces the training computation significantly for large models, but its deployment can…

Sparsely gated Mixture-of-Expert (MoE) has demonstrated its effectiveness in scaling up deep neural networks to an extreme scale. Despite that numerous efforts have been made to improve the performance of MoE from the model design or system…

Machine Learning · Computer Science 2023-02-21 Chang Chen , Min Li , Zhihua Wu , Dianhai Yu , Chao Yang

Sparse Mixture-of-Experts (MoE) architectures effectively scale model capacity by activating only a subset of experts for each input token. However, the standard Top-k routing strategy imposes a uniform sparsity pattern that ignores the…

Artificial Intelligence · Computer Science 2025-12-17 Can Jin , Hongwu Peng , Mingcan Xiang , Qixin Zhang , Xiangchi Yuan , Amit Hasan , Ohiremen Dibua , Yifan Gong , Yan Kang , Dimitris N. Metaxas

Mixture-of-Experts (MoE) models scale efficiently by activating only a subset of experts per token, offering a computationally sparse alternative to dense architectures. While prior post-training optimizations, such as inter- and…

Machine Learning · Computer Science 2025-09-04 Krishna Teja Chitty-Venkata , Sandeep Madireddy , Murali Emani , Venkatram Vishwanath

Sparse Mixture-of-Experts (MoE) models scale capacity by routing each token to a small subset of experts. However, their routers exhibit a fundamental trade-off: strong load balancing can suppress expert specialization, while aggressive…

Machine Learning · Computer Science 2026-05-12 Gleb Molodtsov , Alexander Miasnikov , Aleksandr Beznosikov

The scaling of large language models (LLMs) is a critical research area for the efficiency and effectiveness of model training and deployment. Our work investigates the transferability and discrepancies of scaling laws between Dense Models…

Machine Learning · Computer Science 2024-10-10 Siqi Wang , Zhengyu Chen , Bei Li , Keqing He , Min Zhang , Jingang Wang