English
Related papers

Related papers: Stop Looking for Important Tokens in Multimodal La…

200 papers

Large-scale pre-trained language models have contributed significantly to natural language processing by demonstrating remarkable abilities as few-shot learners. However, their effectiveness depends mainly on scaling the model parameters…

Computation and Language · Computer Science 2023-01-26 Ningyu Zhang , Luoqiu Li , Xiang Chen , Shumin Deng , Zhen Bi , Chuanqi Tan , Fei Huang , Huajun Chen

Multimodal Large Language Models (MLLMs) have shown strong reasoning ability, but their high computational and memory costs hinder deployment in resource-constrained settings. While Post-Training Quantization (PTQ) and vision token pruning…

Computer Vision and Pattern Recognition · Computer Science 2026-04-06 Xinhao Wang , Zhonyu Xia , Zhiwei Lin , Zhe Li , Yongtao Wang

Vision-language models (VLMs) often generate massive visual tokens that greatly increase inference latency and memory footprint; while training-free token pruning offers a practical remedy, existing methods still struggle to balance local…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Enwei Tong , Yuanchao Bai , Yao Zhu , Junjun Jiang , Xianming Liu

Vision-Language Models suffer severe KV cache pressure at inference, as a single image often encodes into thousands of tokens. Most existing methods exploit token sparsity through token pruning, but permanently discarding visual content…

Computer Vision and Pattern Recognition · Computer Science 2026-05-20 Beomseok Kang , Dongwon Jo , Jiwon Song , Donghwee Son , Jae-Joon Kim

This paper studies the relative importance of attention heads in Transformer-based models to aid their interpretability in cross-lingual and multi-lingual tasks. Prior research has found that only a few attention heads are important in each…

Computation and Language · Computer Science 2021-08-20 Weicheng Ma , Kai Zhang , Renze Lou , Lili Wang , Soroush Vosoughi

Token reduction accelerates Multimodal Large Language Models (MLLMs) by reducing excessive tokens, but overlooks structural redundancy differences, where critical and redundant modules process identical token loads. For fine-grained…

Machine Learning · Computer Science 2025-11-14 Aoming Liu , Reuben Tan , Boqing Gong , Bryan A. Plummer

Multimodal Large Language Models (MLLMs) typically process a large number of visual tokens, leading to considerable computational overhead, even though many of these tokens are redundant. Existing visual token pruning methods primarily…

Computer Vision and Pattern Recognition · Computer Science 2025-10-29 Jinhong Deng , Wen Li , Joey Tianyi Zhou , Yang He

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

This paper investigates how to efficiently deploy vision transformers on edge devices for small workloads. Recent methods reduce the latency of transformer neural networks by removing or merging tokens, with small accuracy degradation.…

Machine Learning · Computer Science 2024-11-12 Nick John Eliopoulos , Purvish Jajal , James C. Davis , Gaowen Liu , George K. Thiravathukal , Yung-Hsiang Lu

Large Vision Language Models (LVLMs) have been widely adopted to guide vision foundation models in performing reasoning segmentation tasks, achieving impressive performance. However, the substantial computational overhead associated with…

Computer Vision and Pattern Recognition · Computer Science 2025-04-16 Hanning Chen , Yang Ni , Wenjun Huang , Hyunwoo Oh , Yezi Liu , Tamoghno Das , Mohsen Imani

The computational demands of Vision Transformers (ViTs) and Vision-Language Models (VLMs) remain a significant challenge due to the quadratic complexity of self-attention. While token pruning offers a promising solution, existing methods…

Computer Vision and Pattern Recognition · Computer Science 2025-03-17 Ahmadreza Jeddi , Negin Baghbanzadeh , Elham Dolatabadi , Babak Taati

Vision-Language-Action (VLA) models have achieved significant breakthroughs by leveraging Large Vision Language Models (VLMs) to jointly interpret instructions and visual inputs. However, the substantial increase in visual tokens,…

Robotics · Computer Science 2026-02-25 Haosheng Li , Weixin Mao , Zihan Lan , Hongwei Xiong , Hongan Wang , Chenyang Si , Ziwei Liu , Xiaoming Deng , Hua Chen

Token pruning methods for Vision Transformers (ViTs) promise quadratic reductions in attention FLOPs by dropping uninformative patches. Yet standard variable-length attention APIs -- including FlashAttention-2's varlen and PyTorch's…

Machine Learning · Computer Science 2026-05-13 Seifeldin Abdellatif , Ahmad Almasri

Real-world deployment of Vision-Language Models (VLMs) is hindered by high computational demands, as existing architectures inefficiently process all tokens uniformly. We introduce Adaptive Token Pruning (ATP), a dynamic inference mechanism…

Computer Vision and Pattern Recognition · Computer Science 2025-12-16 Xue Li , Xiaonan Song , Henry Hu

Generative recommendation systems typically leverage Semantic Identifiers (SIDs), which represent each item as a sequence of tokens that encode semantic information. However, representing item ID with multiple SIDs significantly increases…

Information Retrieval · Computer Science 2026-01-27 Tianyu Zhan , Kairui Fu , Zheqi Lv , Shengyu Zhang

Large Vision Language Models (LVLMs) have achieved significant success across multi-modal tasks. However, the computational cost of processing long visual tokens can be prohibitively expensive on resource-limited devices. Previous methods…

Computer Vision and Pattern Recognition · Computer Science 2024-12-03 Xubing Ye , Yukang Gan , Yixiao Ge , Xiao-Ping Zhang , Yansong Tang

Autoregressive Transformers adopted in Large Language Models (LLMs) are hard to scale to long sequences. Despite several works trying to reduce their computational cost, most of LLMs still adopt attention layers between all pairs of tokens…

Computation and Language · Computer Science 2024-06-03 Sotiris Anagnostidis , Dario Pavllo , Luca Biggio , Lorenzo Noci , Aurelien Lucchi , Thomas Hofmann

Recent advances in deep learning rely heavily on massive datasets, leading to substantial storage and training costs. Dataset pruning aims to alleviate this demand by discarding redundant examples. However, many existing methods require…

Machine Learning · Computer Science 2025-06-13 Yeseul Cho , Baekrok Shin , Changmin Kang , Chulhee Yun

Vision-Language Models (VLMs) have achieved remarkable progress in multimodal reasoning and generation, yet their high computational demands remain a major challenge. Diffusion Vision-Language Models (DVLMs) are particularly attractive…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Jingqi Xu , Jingxi Lu , Chenghao Li , Sreetama Sarkar , Souvik Kundu , Peter A. Beerel

Unified multimodal transformers, which handle both generation and understanding tasks within a shared parameter space, have received increasing attention in recent research. Although various unified transformers have been proposed, training…

Computer Vision and Pattern Recognition · Computer Science 2025-02-11 Weijia Mao , Zhenheng Yang , Mike Zheng Shou