English
Related papers

Related papers: More Experts Than Galaxies: Conditionally-overlapp…

200 papers

Mixture-of-Experts (MoE) architectures employ sparse activation to deliver faster training and inference with higher accuracy than dense LLMs. However, in production serving, MoE models require batch inference to optimize hardware…

Machine Learning · Computer Science 2026-02-10 Juntong Wu , Jialiang Cheng , Fuyu Lv , Ou Dan , Li Yuan

Sparse Mixture of Experts (SMoE) enables efficient training of large language models by routing input tokens to a select number of experts. However, training SMoE remains challenging due to the issue of representation collapse. Recent…

Computation and Language · Computer Science 2025-04-01 Giang Do , Hung Le , Truyen Tran

Continual learning (CL) has garnered significant attention because of its ability to adapt to new tasks that arrive over time. Catastrophic forgetting (of old tasks) has been identified as a major issue in CL, as the model adapts to new…

Machine Learning · Computer Science 2025-02-20 Hongbo Li , Sen Lin , Lingjie Duan , Yingbin Liang , Ness B. Shroff

Sparse Mixture-of-Experts (MoE) models can outperform dense large language models at similar computation by activating only a small set of experts per token. However, stacking many expert modules introduces substantial parameter memory,…

Artificial Intelligence · Computer Science 2026-04-03 Xin He , Shunkang Zhang , Kaijie Tang , Shaohuai Shi , Yuxin Wang , Zihao Zeng , Zhenheng Tang , Xiaowen Chu , Haiyan Yin , Ivor W. Tsang , Yew Soon Ong

The automatic generation of high-quality mathematical problems is practically valuable in many educational scenarios. Large multimodal model provides a novel technical approach for the mathematical problem generation because of its wide…

Artificial Intelligence · Computer Science 2024-07-17 Sannyuya Liu , Jintian Feng , Zongkai Yang , Yawei Luo , Qian Wan , Xiaoxuan Shen , Jianwen Sun

Understanding the internal computations of large language models (LLMs) is crucial for aligning them with human values and preventing undesirable behaviors like toxic content generation. However, mechanistic interpretability is hindered by…

Artificial Intelligence · Computer Science 2025-06-12 Jungwoo Park , Young Jin Ahn , Kee-Eung Kim , Jaewoo Kang

A widely used paradigm to improve the generalization performance of high-capacity neural models is through the addition of auxiliary unsupervised tasks during supervised training. Tasks such as similarity matching and input reconstruction…

Machine Learning · Computer Science 2022-01-19 Shivin Srivastava , Kenji Kawaguchi , Vaibhav Rajan

While transformers and their variant conformers show promising performance in speech recognition, the parameterized property leads to much memory cost during training and inference. Some works use cross-layer weight-sharing to reduce the…

Audio and Speech Processing · Electrical Eng. & Systems 2022-09-20 Ye Bai , Jie Li , Wenjing Han , Hao Ni , Kaituo Xu , Zhuo Zhang , Cheng Yi , Xiaorui Wang

Rapid advancements in deep learning have led to many recent breakthroughs. While deep learning models achieve superior performance, often statistically better than humans, their adoption into safety-critical settings, such as healthcare or…

Machine Learning · Computer Science 2022-04-08 Marko Vasic , Andrija Petrovic , Kaiyuan Wang , Mladen Nikolic , Rishabh Singh , Sarfraz Khurshid

With the recent advancements of deep learning technologies, the performance of voice conversion (VC) in terms of quality and similarity has been significantly improved. However, heavy computations are generally required for…

Sound · Computer Science 2019-12-30 Yu-Tao Chang , Yuan-Hong Yang , Yu-Huai Peng , Syu-Siang Wang , Tai-Shih Chi , Yu Tsao , Hsin-Min Wang

Multimodal recommendation enhances ranking by integrating user-item interactions with item content, which is particularly effective under sparse feedback and long-tail distributions. However, multimodal signals are inherently heterogeneous…

Artificial Intelligence · Computer Science 2026-02-27 Ji Dai , Quan Fang , Dengsheng Cai

The combination and aggregation of knowledge from multiple neural networks can be commonly seen in the form of mixtures of experts. However, such combinations are usually done using networks trained on the same tasks, with little mention of…

Machine Learning · Computer Science 2021-03-26 Chen Wen Kang , Chua Meng Hong , Tomas Maul

Prompt-based methods have recently gained prominence in Continual Learning (CL) due to their strong performance and memory efficiency. A prevalent strategy in this paradigm assigns a dedicated subset of prompts to each task, which, while…

Machine Learning · Computer Science 2026-03-12 Minh Le , Bao-Ngoc Dao , Huy Nguyen , Quyen Tran , Anh Nguyen , Nhat Ho

Mixture of experts method is a neural network based ensemble learning that has great ability to improve the overall classification accuracy. This method is based on the divide and conquer principle, in which the problem space is divided…

Machine Learning · Computer Science 2021-05-26 Laleh Armi , Elham Abbasi , Jamal Zarepour-Ahmadabadi

Modern machine learning accelerators are designed to efficiently execute deep neural networks (DNNs) by optimizing data movement, memory hierarchy, and compute throughput. However, emerging DNN models such as large language models, state…

Hardware Architecture · Computer Science 2025-09-03 Shubham Negi , Manik Singhal , Aayush Ankit , Sudeep Bhoja , Kaushik Roy

The traditional viewpoint on Sparse Mixture of Experts (MoE) models is that instead of training a single large expert, which is computationally expensive, we can train many small experts. The hope is that if the total parameter count of the…

Machine Learning · Computer Science 2024-09-04 Youngseog Chung , Dhruv Malik , Jeff Schneider , Yuanzhi Li , Aarti Singh

Mixture-of-Experts (MoE) models are often interpreted by analysing which categories are routed to which experts. However, routing alone does not reveal what each expert actually encodes. We train sparsely-gated convolutional MoE models with…

Computer Vision and Pattern Recognition · Computer Science 2026-05-21 Gene Tangtartharakul , Katherine R. Storrs

Training wide and deep neural networks (DNNs) require large amounts of storage resources such as memory because the intermediate activation data must be saved in the memory during forward propagation and then restored for backward…

Artificial Intelligence · Computer Science 2021-11-19 Sian Jin , Chengming Zhang , Xintong Jiang , Yunhe Feng , Hui Guan , Guanpeng Li , Shuaiwen Leon Song , Dingwen Tao

Sparse mixture of experts (SMoE) have emerged as an effective approach for scaling large language models while keeping a constant computational cost. Regardless of several notable successes of SMoE, effective training such architecture…

Computation and Language · Computer Science 2024-06-25 Giang Do , Hung Le , Truyen Tran

Large language models, such as OpenAI's ChatGPT, have demonstrated exceptional language understanding capabilities in various NLP tasks. Sparsely activated mixture-of-experts (MoE) has emerged as a promising solution for scaling models…

Computation and Language · Computer Science 2023-10-12 Jiamin Li , Qiang Su , Yitao Yang , Yimin Jiang , Cong Wang , Hong Xu