English
Related papers

Related papers: FastMMoE: Accelerating Multimodal Large Language M…

200 papers

Mixture-of-Experts (MoE) models enable efficient scaling of large language models (LLMs) by activating only a subset of experts per input. However, we observe that the commonly used auxiliary load balancing loss often leads to expert…

Computation and Language · Computer Science 2026-01-27 Hongcan Guo , Haolang Lu , Guoshun Nan , Bolun Chu , Jialin Zhuang , Yuan Yang , Wenhao Che , Xinye Cao , Sicong Leng , Qimei Cui , Xudong Jiang

As the computational needs of Large Vision-Language Models (LVLMs) increase, visual token pruning has proven effective in improving inference speed and memory efficiency. Traditional pruning methods in LVLMs predominantly focus on attention…

Computer Vision and Pattern Recognition · Computer Science 2025-03-12 Bozhi Luan , Wengang Zhou , Hao Feng , Zhe Wang , Xiaosong Li , Houqiang Li

Multimodal large language models (MLLMs) have shown remarkable performance for cross-modal understanding and generation, yet still suffer from severe inference costs. Recently, abundant works have been proposed to solve this problem with…

Computation and Language · Computer Science 2025-05-30 Zichen Wen , Yifeng Gao , Weijia Li , Conghui He , Linfeng Zhang

Mixture-of-Experts (MoE) has become a dominant architecture for scaling large language models due to their sparse activation mechanism. However, the substantial number of expert activations creates a critical latency bottleneck during…

Machine Learning · Computer Science 2026-04-10 Baihui Liu , Kaiyuan Tian , Wei Wang , Zhaoning Zhang , Linbo Qiao , Dongsheng Li

Video large language models (video LLMs) excel at video comprehension but face significant computational inefficiency due to redundant video tokens. Existing token pruning methods offer solutions. However, approaches operating within the…

Computer Vision and Pattern Recognition · Computer Science 2025-10-13 Kele Shao , Keda Tao , Can Qin , Haoxuan You , Yang Sui , Huan Wang

Mixture-of-Experts (MoE) architectures scale language models by activating only a subset of specialized expert networks for each input token, thereby reducing the number of floating-point operations. However, the growing size of modern MoE…

Machine Learning · Computer Science 2025-11-14 Yun Wang , Lingyun Yang , Senhao Yu , Yixiao Wang , Ruixing Li , Zhixiang Wei , James Yen , Zhengwei Qi

Video large language models (VLLMs) have significantly advanced recently in processing complex video content, yet their inference efficiency remains constrained because of the high computational cost stemming from the thousands of visual…

Computer Vision and Pattern Recognition · Computer Science 2025-03-31 Keda Tao , Can Qin , Haoxuan You , Yang Sui , Huan Wang

Multimodal large language models (MLLMs) improve performance on vision-language tasks by integrating visual features from pre-trained vision encoders into large language models (LLMs). However, how MLLMs process and utilize visual…

Computer Vision and Pattern Recognition · Computer Science 2025-03-18 Hao Yin , Guangzong Si , Zilei Wang

Despite a big leap forward in capability, multimodal large language models (MLLMs) tend to behave like a sloth in practical use, i.e., slow response and large latency. Recent efforts are devoted to building tiny MLLMs for better efficiency,…

Computer Vision and Pattern Recognition · Computer Science 2024-12-06 Bo Tong , Bokai Lai , Yiyi Zhou , Gen Luo , Yunhang Shen , Ke Li , Xiaoshuai Sun , Rongrong Ji

Multimodal large language models (MLLMs) have recently demonstrated strong capabilities in understanding and generating responses from diverse visual inputs, including high-resolution images and long video sequences. As these models scale…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Junwan Kim , Hyunkyung Bae

Sparsely activated Mixture-of-Experts (MoE) models are widely adopted to scale up model capacity without increasing the computation budget. However, vanilla TopK routers are trained in a discontinuous, non-differentiable way, limiting their…

Machine Learning · Computer Science 2025-02-28 Ziteng Wang , Jun Zhu , Jianfei Chen

Large Vision-Language Models (LVLMs) rely on dense visual tokens to capture fine-grained visual information, but processing all these tokens incurs substantial computational and memory overhead during inference. To address this issue, we…

Machine Learning · Computer Science 2026-03-24 Xu Li , Yi Zheng , Yuxuan Liang , Zhe Liu , Xiaolei Chen , Haotian Chen , Rui Zhu , Xiangyang Xue

Mixture of experts (MoE) architectures have become a cornerstone for scaling up and are a key component in most large language models such as GPT-OSS, DeepSeek-V3, Llama-4, and Gemini-2.5. However, systematic research on MoE remains…

Computation and Language · Computer Science 2026-02-11 Nam V. Nguyen , Thong T. Doan , Luong Tran , Van Nguyen , Quang Pham

Mixture-of-Experts (MoE) in Large Language Models (LLMs) routes each token through a subset of specialized Feed-Forward Networks (FFN), known as experts. We present SteerMoE, a framework to steer MoE models by detecting and controlling…

Computation and Language · Computer Science 2026-02-13 Mohsen Fayyaz , Ali Modarressi , Hanieh Deilamsalehy , Franck Dernoncourt , Ryan Rossi , Trung Bui , Hinrich Schütze , Nanyun Peng

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

In the era of Large Language Models (LLMs), Mixture-of-Experts (MoE) architectures offer a promising approach to managing computational costs while scaling up model parameters. Conventional MoE-based LLMs typically employ static Top-K…

Computation and Language · Computer Science 2024-10-16 Tongtian Yue , Longteng Guo , Jie Cheng , Xuange Gao , Jing Liu

Among parallel decoding paradigms, diffusion large language models (dLLMs) have emerged as a promising candidate that balances generation quality and throughput. However, their integration with Mixture-of-Experts (MoE) architectures is…

Machine Learning · Computer Science 2026-02-03 Hao Mark Chen , Zhiwen Mo , Royson Lee , Qianzhou Wang , Da Li , Shell Xu Hu , Wayne Luk , Timothy Hospedales , Hongxiang Fan

Continually expanding new languages for existing large language models (LLMs) is a promising yet challenging approach to building powerful multilingual LLMs. The biggest challenge is to make the model continuously learn new languages while…

Computation and Language · Computer Science 2025-05-29 Xue Zhang , Yunlong Liang , Fandong Meng , Songming Zhang , Yufeng Chen , Jinan Xu , Jie Zhou

Despite LLMs' excellent code creation capabilities, multilingual code generation remains extremely challenging. To address this, we intent to improve the multi-programming-lingual (MultiPL) performance of the base LLMs while retaining the…

Computation and Language · Computer Science 2025-09-09 Qing Wang , Xue Han , Jiahui Wang , Lehao Xing , Qian Hu , Lianlian Zhang , Chao Deng , Junlan Feng

Mixture-of-Experts (MoE) Large Language Models (LLMs) efficiently scale-up the model while keeping relatively low inference cost. As MoE models only activate part of the experts, related work has proposed expert prediction and caching…

Computation and Language · Computer Science 2025-11-17 Shien Zhu , Samuel Bohl , Robin Oester , Gustavo Alonso