English
Related papers

Related papers: Training-Free Acceleration of ViTs with Delayed Sp…

200 papers

Over the past few years, vision transformers (ViTs) have consistently demonstrated remarkable performance across various visual recognition tasks. However, attempts to enhance their robustness have yielded limited success, mainly focusing…

Computer Vision and Pattern Recognition · Computer Science 2024-10-01 Nick Nikzad , Yi Liao , Yongsheng Gao , Jun Zhou

Video large language models (Video-LLMs) face high computational costs due to large volumes of visual tokens. Existing token compression methods typically adopt a two-stage spatiotemporal compression strategy, relying on stage-specific…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Junhao Du , Jialong Xue , Anqi Li , Jincheng Dai , Guo Lu

Vision-language models (VLMs) have achieved remarkable multimodal understanding and reasoning capabilities, yet remain computationally expensive due to dense visual tokenization. Existing efficiency approaches either merge redundant visual…

Computer Vision and Pattern Recognition · Computer Science 2026-03-30 Aditya Kumar Singh , Hitesh Kandala , Pratik Prabhanjan Brahma , Zicheng Liu , Emad Barsoum

Vision-Language Models (VLMs) have become essential backbones of modern multimodal intelligence, yet their outputs remain prone to hallucination-plausible text misaligned with visual inputs. Existing alignment approaches often rely on…

Computer Vision and Pattern Recognition · Computer Science 2025-10-28 Kejia Chen , Jiawen Zhang , Jiacong Hu , Kewei Gao , Jian Lou , Zunlei Feng , Mingli Song

Instructed Visual Segmentation (IVS) tasks require segmenting objects in images or videos based on natural language instructions. While recent multimodal large language models (MLLMs) have achieved strong performance on IVS, their inference…

Computer Vision and Pattern Recognition · Computer Science 2025-08-19 Wenhui Zhu , Xiwen Chen , Zhipeng Wang , Shao Tang , Sayan Ghosh , Xuanzhao Dong , Rajat Koner , Yalin Wang

Vision Transformers (ViTs) have demonstrated remarkable potential in image processing tasks by utilizing self-attention mechanisms to capture global relationships within data. However, their scalability is hindered by significant…

Machine Learning · Computer Science 2026-02-25 Huy Trinh , Rebecca Ma , Zeqi Yu , Tahsin Reza

We propose Confidence-Guided Token Merging (Co-Me), an acceleration mechanism for visual geometric transformers without retraining or finetuning the base model. Co-Me distilled a light-weight confidence predictor to rank tokens by…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Yutian Chen , Yuheng Qiu , Ruogu Li , Ali Agha , Shayegan Omidshafiei , Jay Patrikar , Sebastian Scherer

The recently developed vision transformer (ViT) has achieved promising results on image classification compared to convolutional neural networks. Inspired by this, in this paper, we study how to learn multi-scale feature representations in…

Computer Vision and Pattern Recognition · Computer Science 2021-08-24 Chun-Fu Chen , Quanfu Fan , Rameswar Panda

Recently, Vision Transformer (ViT) has achieved remarkable success in several computer vision tasks. The progresses are highly relevant to the architecture design, then it is worthwhile to propose Transformer Architecture Search (TAS) to…

Computer Vision and Pattern Recognition · Computer Science 2022-03-24 Qinqin Zhou , Kekai Sheng , Xiawu Zheng , Ke Li , Xing Sun , Yonghong Tian , Jie Chen , Rongrong Ji

The integration of visual inputs with large language models (LLMs) has led to remarkable advancements in multi-modal capabilities, giving rise to visual large language models (VLLMs). However, effectively harnessing VLLMs for intricate…

Computer Vision and Pattern Recognition · Computer Science 2023-11-14 Renjie Pi , Lewei Yao , Jiahui Gao , Jipeng Zhang , Tong Zhang

The groundbreaking performance of transformers in Natural Language Processing (NLP) tasks has led to their replacement of traditional Convolutional Neural Networks (CNNs), owing to the efficiency and accuracy achieved through the…

Computer Vision and Pattern Recognition · Computer Science 2024-08-13 Gousia Habib , Damandeep Singh , Ishfaq Ahmad Malik , Brejesh Lall

Modern multimodal large language models (MLLMs) typically keep the language model fixed and train a visual projector that maps the pixels into a sequence of tokens in its embedding space, so that images can be presented in essentially the…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Hyun Lee , Hyemin Jeong , Yejin Kim , Hyungwook Choi , Hyunsoo Cho , Soo Kyung Kim , Joonseok Lee

Vision Transformers (ViTs) have shown impressive performance and have become a unified backbone for multiple vision tasks. However, both the attention mechanism and multi-layer perceptrons (MLPs) in ViTs are not sufficiently efficient due…

Machine Learning · Computer Science 2024-07-26 Haoran You , Huihong Shi , Yipin Guo , Yingyan Celine Lin

Due to the auto-regressive nature of current video large language models (Video-LLMs), the inference latency increases as the input sequence length grows, posing challenges for the efficient processing of video sequences that are usually…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Xuan Zhang , Cunxiao Du , Sicheng Yu , Jiawei Wu , Fengzhuo Zhang , Wei Gao , Qian Liu

Multimodal large language models (MLLMs) demand considerable computations for inference due to the extensive parameters and the additional input tokens needed for visual information representation. Herein, we introduce Visual Tokens…

Computer Vision and Pattern Recognition · Computer Science 2025-01-28 Zhihang Lin , Mingbao Lin , Luxi Lin , Rongrong Ji

Visual language models encounter challenges in computational efficiency and latency, primarily due to the substantial redundancy in the token representations of high-resolution images and videos. Current attention/similarity-based…

Computer Vision and Pattern Recognition · Computer Science 2025-12-11 Dehua Zheng , Mouxiao Huang , Borui Jiang , Hailin Hu , Xinghao Chen

The Vision Transformer (ViT) has gained prominence for its superior relational modeling prowess. However, its global attention mechanism's quadratic complexity poses substantial computational burdens. A common remedy spatially groups tokens…

Computer Vision and Pattern Recognition · Computer Science 2025-07-03 Qihang Fan , Huaibo Huang , Mingrui Chen , Ran He

The hierarchical architecture has become a mainstream design paradigm for Vision Transformers (ViTs), with Patch Merging serving as the pivotal component that transforms a columnar architecture into a hierarchical one. Drawing inspiration…

Computer Vision and Pattern Recognition · Computer Science 2025-06-17 Yonghao Yu , Dongcheng Zhao , Guobin Shen , Yiting Dong , Yi Zeng

Can we use sparse tokens for dense prediction, e.g., segmentation? Although token sparsification has been applied to Vision Transformers (ViT) to accelerate classification, it is still unknown how to perform segmentation from sparse tokens.…

Computer Vision and Pattern Recognition · Computer Science 2023-03-14 Lei Zhou , Huidong Liu , Joseph Bae , Junjun He , Dimitris Samaras , Prateek Prasanna

Multi-task model merging offers a promising paradigm for integrating multiple expert models into a unified model without additional training. Existing state-of-the-art techniques, such as Task Arithmetic and its variants, merge models by…

Artificial Intelligence · Computer Science 2025-05-15 Wenju Sun , Qingyong Li , Yangli-ao Geng , Boyang Li