English
Related papers

Related papers: Leveraging KV Similarity for Online Structured Pru…

200 papers

Structured pruning of modern large language models (LLMs) has emerged as a way of decreasing their high computational needs. Width pruning reduces the size of projection weight matrices (e.g., by removing attention heads) while maintaining…

Machine Learning · Computer Science 2024-06-25 Bo-Kyeong Kim , Geonmin Kim , Tae-Ho Kim , Thibault Castells , Shinkook Choi , Junho Shin , Hyoung-Kyu Song

Large Multimodal Models (LMMs) have emerged as powerful models capable of understanding various data modalities, including text, images, and videos. LMMs encode both text and visual data into tokens that are then combined and processed by…

Computer Vision and Pattern Recognition · Computer Science 2025-04-03 Saeed Ranjbar Alvar , Gursimran Singh , Mohammad Akbari , Yong Zhang

Vision Language Models (VLMs) struggle with long-form videos due to the quadratic complexity of attention mechanisms. We propose Language-Guided Temporal Token Pruning (LGTTP), which leverages temporal cues from queries to adaptively prune…

Computer Vision and Pattern Recognition · Computer Science 2025-08-26 Yogesh Kumar

The remarkable performance of large language models (LLMs) in various language tasks has attracted considerable attention. However, the ever-increasing size of these models presents growing challenges for deployment and inference.…

Computation and Language · Computer Science 2025-02-21 Jiayu Qin , Jianchao Tan , Kefeng Zhang , Xunliang Cai , Wei Wang

Due to the prevalence of large language models (LLMs), key-value (KV) cache reduction for LLM inference has received remarkable attention. Among numerous works that have been proposed in recent years, layer-wise token pruning approaches,…

Computation and Language · Computer Science 2026-04-17 Rei Taniguchi , Yuyang Dong , Makoto Onizuka , Chuan Xiao

Visual token pruning methods effectively mitigate the quadratic computational growth caused by processing high-resolution images and video frames in vision-language models (VLMs). However, existing approaches rely on predefined pruning…

Computer Vision and Pattern Recognition · Computer Science 2026-04-17 Huawei Ji , Yuanhao Sun , Yuan Jin , Cheng Deng , Jiaxin Ding , Luoyi Fu , Xinbing Wang

Token filtering has been proposed to enhance the utility of large language models (LLMs) by eliminating inconsequential tokens during training. While usingfewer tokens is expected to reduce computational workloads, existing methods have not…

Machine Learning · Computer Science 2026-03-20 Di Chai , Pengbo Li , Feiyuan Zhang , Yilun Jin , Han Tian , Kaiqiang Xu , Binhang Yuan , Dian Shen , Junxue Zhang , Kai Chen

Discrete diffusion-based multimodal large language models (dMLLMs) have emerged as a promising alternative to autoregressive MLLMs thanks to their advantages in parallel decoding and bidirectional context modeling, but most existing dMLLMs…

Computer Vision and Pattern Recognition · Computer Science 2025-11-20 Duo Li , Zuhao Yang , Xiaoqin Zhang , Ling Shao , Shijian Lu

While multi-modal large language models (MLLMs) have made significant progress in recent years, the issue of hallucinations remains a major challenge. To mitigate this phenomenon, existing solutions either introduce additional data for…

Computer Vision and Pattern Recognition · Computer Science 2025-10-23 Fengyuan Sun , Hui Chen , Xinhao Xu , Dandan Zheng , Jingdong Chen , Jun Zhou , Jungong Han , Guiguang Ding

By treating visual tokens from visual encoders as text tokens, Multimodal Large Language Models (MLLMs) have achieved remarkable progress across diverse visual understanding tasks, leveraging the robust architectures of Large Language…

Computer Vision and Pattern Recognition · Computer Science 2024-12-03 Zeliang Zhang , Phu Pham , Wentian Zhao , Kun Wan , Yu-Jhe Li , Jianing Zhou , Daniel Miranda , Ajinkya Kale , Chenliang Xu

Vision tokens in multimodal large language models often dominate huge computational overhead due to their excessive length compared to linguistic modality. Abundant recent methods aim to solve this problem with token pruning, which first…

Computation and Language · Computer Science 2025-06-10 Zichen Wen , Yifeng Gao , Shaobo Wang , Junyuan Zhang , Qintong Zhang , Weijia Li , Conghui He , Linfeng Zhang

Visual tokens dominate inference cost in vision-language models (VLMs), yet many carry redundant information. Existing pruning methods alleviate this but typically rely on attention magnitude or similarity scores. We reformulate visual…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Landi He , Xiaoyu Yang , Lijian Xu

To remove redundant components of large language models (LLMs) without incurring significant computational costs, this work focuses on single-shot pruning without a retraining phase. We simplify the pruning process for Transformer-based…

Artificial Intelligence · Computer Science 2024-07-30 Jianwei Li , Yijun Dong , Qi Lei

Large Language Models (LLMs) have long held sway in the realms of artificial intelligence research. Numerous efficient techniques, including weight pruning, quantization, and distillation, have been embraced to compress LLMs, targeting…

Artificial Intelligence · Computer Science 2024-11-01 Xuan Shen , Pu Zhao , Yifan Gong , Zhenglun Kong , Zheng Zhan , Yushu Wu , Ming Lin , Chao Wu , Xue Lin , Yanzhi Wang

Vision-Language Models (VLMs) have advanced rapidly within the unified Transformer architecture, yet their deployment on resource-constrained devices remains challenging due to high computational complexity. While pruning has emerged as an…

Computer Vision and Pattern Recognition · Computer Science 2026-04-06 Zimeng Wu , Yunhong Wang , Donghao Wang , Jiaxin Chen

Token compression is essential for reducing the computational and memory requirements of transformer models, enabling their deployment in resource-constrained environments. In this work, we propose an efficient and hardware-compatible token…

Computer Vision and Pattern Recognition · Computer Science 2025-04-01 Junzhu Mao , Yang Shen , Jinyang Guo , Yazhou Yao , Xiansheng Hua

The high inference cost of Large Language Models (LLMs) poses challenges, especially for tasks requiring lengthy outputs. However, natural language often contains redundancy, which presents an opportunity for optimization. We have observed…

Computation and Language · Computer Science 2025-11-25 Alfredo Garrachón Ruiz , Tomás de la Rosa , Daniel Borrajo

Large language models (LLMs) improve reasoning accuracy when generating multiple candidate solutions at test time, but standard methods like Best-of-N (BoN) incur high computational cost by fully generating all branches. Self-Truncation…

Machine Learning · Computer Science 2025-11-05 Sophie Li , Nicholas Huang , Nayan Saxena , Nina Luo , Vincent Lin , Kevin Zhu , Sunishchal Dev

Deep neural networks have been the predominant paradigm in machine learning for solving cognitive tasks. Such models, however, are restricted by a high computational overhead, limiting their applicability and hindering advancements in the…

Machine Learning · Computer Science 2024-11-05 Ian Pons , Bruno Yamamoto , Anna H. Reali Costa , Artur Jordao

Diffusion-based large multimodal models, such as LLaDA-V, have demonstrated impressive capabilities in vision-language understanding and generation. However, their bidirectional attention mechanism and diffusion-style iterative denoising…

Computer Vision and Pattern Recognition · Computer Science 2026-01-29 Zhewen Wan , Tianchen Song , Chen Lin , Zhiyong Zhao , Xianpeng Lang