English
Related papers

Related papers: Mixture-of-Recursions: Learning Dynamic Recursive …

200 papers

Mixture-of-Experts (MoE) is a promising way to scale up the learning capacity of large language models. It increases the number of parameters while keeping FLOPs nearly constant during inference through sparse activation. Yet, it still…

Machine Learning · Computer Science 2025-02-26 Pingzhi Li , Xiaolong Jin , Zhen Tan , Yu Cheng , Tianlong Chen

Low-rank adaptation (LoRA) and its mixture-of-experts (MOE) variants are highly effective parameter-efficient fine-tuning (PEFT) methods. However, they introduce significant latency in multi-tenant settings due to the LoRA modules and MOE…

Computation and Language · Computer Science 2024-10-24 Jingfan Zhang , Yi Zhao , Dan Chen , Xing Tian , Huanran Zheng , Wei Zhu

Mixture-of-Experts large language models (MoE-LLMs) marks a significant step forward of language models, however, they encounter two critical challenges in practice: 1) expert parameters lead to considerable memory consumption and loading…

Machine Learning · Computer Science 2025-02-25 Wei Huang , Yue Liao , Jianhui Liu , Ruifei He , Haoru Tan , Shiming Zhang , Hongsheng Li , Si Liu , Xiaojuan Qi

Mixture-of-Experts (MoE), a conditional computation architecture, achieved promising performance by scaling local module (i.e. feed-forward network) of transformer. However, scaling the cross-token module (i.e. self-attention) is…

Machine Learning · Computer Science 2022-01-17 Yuxuan Lou , Fuzhao Xue , Zangwei Zheng , Yang You

Sparsely Mixture of Experts (MoE) has received great interest due to its promising scaling capability with affordable computational overhead. MoE converts dense layers into sparse experts, and utilizes a gated routing network to make…

Computation and Language · Computer Science 2022-07-20 Yuan Xie , Shaohan Huang , Tianyu Chen , Furu Wei

The increasing demand for deploying large Mixture-of-Experts (MoE) models in resource-constrained environments necessitates efficient approaches to address their high memory and computational requirements challenges. Moreover, given that…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-09-10 HamidReza Imani , Abdolah Amirany , Tarek El-Ghazawi

Recurrent LLM architectures have emerged as a promising approach for improving reasoning, as they enable multi-step computation in the embedding space without generating intermediate tokens. Models such as Ouro perform reasoning by…

Mixture-of-Experts (MoE) presents a naturally compatible and scalable framework for multimodal learning, demonstrating strong adaptability across diverse modalities and tasks. Despite its growing success, a comprehensive and systematic…

Machine Learning · Computer Science 2026-05-28 Liangwei Nathan Zheng , Wei Emma Zhang , Olaf Maennel , Lin Yue , Weitong Chen

Mixture-of-Experts (MoE) architecture offers enhanced efficiency for Large Language Models (LLMs) with modularized computation, yet its inherent sparsity poses significant hardware deployment challenges, including memory locality issues,…

Hardware Architecture · Computer Science 2026-03-10 Shuqing Luo , Ye Han , Pingzhi Li , Jiayin Qin , Jie Peng , Yang , Zhao , Yu , Cao , Tianlong Chen

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,…

With distributed machine learning being a prominent technique for large-scale machine learning tasks, communication complexity has become a major bottleneck for speeding up training and scaling up machine numbers. In this paper, we propose…

Machine Learning · Computer Science 2023-09-26 Pengyun Yue , Hanzhen Zhao , Cong Fang , Di He , Liwei Wang , Zhouchen Lin , Song-chun Zhu

Large language models (LLMs) have demonstrated remarkable success across diverse artificial intelligence tasks, driven by scaling laws that correlate model size and training data with performance improvements. However, this scaling paradigm…

Machine Learning · Computer Science 2025-11-13 Tong Wu , Yutong He , Bin Wang , Kun Yuan

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

The Mixture of Experts (MoE) architecture enables the scaling of Large Language Models (LLMs) to trillions of parameters by activating a sparse subset of weights for each input, maintaining constant computational cost during inference.…

Machine Learning · Computer Science 2026-01-08 Shihao Ji , Zihui Song

Transformer models face scalability challenges in causal language modeling (CLM) due to inefficient memory allocation for growing key-value (KV) caches, which strains compute and storage resources. Existing methods like Grouped Query…

Computation and Language · Computer Science 2025-06-17 Guanghui Song , Dongping Liao , Yiren Zhao , Kejiang Ye , Cheng-zhong Xu , Xitong Gao

Recently, residual reconstruction-based model quantization methods have achieved promising performance in low-bit post-training quantization (PTQ) by introducing cross-layer residuals to reduce error accumulated from previous…

Machine Learning · Computer Science 2026-05-19 Le Su , Xing Luo , Zhi Jin

The visual medium (images and videos) naturally contains a large amount of information redundancy, thereby providing a great opportunity for leveraging efficiency in processing. While Vision Transformer (ViT) based models scale effectively…

Computer Vision and Pattern Recognition · Computer Science 2024-07-31 Gagan Jain , Nidhi Hegde , Aditya Kusupati , Arsha Nagrani , Shyamal Buch , Prateek Jain , Anurag Arnab , Sujoy Paul

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

Representation learning on multi-omics data is challenging due to extreme dimensionality, modality heterogeneity, and cohort-specific batch effects. While pre-trained transformer backbones have shown broad generalization capabilities in…

Machine Learning · Computer Science 2025-11-27 Audrey Pei-Hsuan Chen