English
Related papers

Related papers: EchoingPixels: Cross-Modal Adaptive Token Reductio…

200 papers

Multimodal Large Language Models (MLLMs) encounter significant computational and memory bottlenecks from the massive number of visual tokens generated by high-resolution images or multi-image inputs. Previous token compression techniques…

Computer Vision and Pattern Recognition · Computer Science 2025-10-21 Jiaying Zhu , Yurui Zhu , Xin Lu , Wenrui Yan , Dong Li , Kunlin Liu , Xueyang Fu , Zheng-Jun Zha

Multimodal large language models (MLLMs) have advanced perception across text, vision, and audio, yet they often struggle with structured cross-modal reasoning, particularly when integrating audio and visual signals. We introduce…

Computer Vision and Pattern Recognition · Computer Science 2025-06-20 Zhenghao Xing , Xiaowei Hu , Chi-Wing Fu , Wenhai Wang , Jifeng Dai , Pheng-Ann Heng

Large Multimodal Models (LMMs) have proven effective on various tasks. They typically encode visual inputs into Original Model sequences of tokens, which are then concatenated with textual tokens and jointly processed by the language model.…

Computer Vision and Pattern Recognition · Computer Science 2026-01-01 Hao Zhang , Mengsi Lyu , Bo Huang , Yulong Ao , Yonghua Lin

Cross-modal alignment Learning integrates information from different modalities like text, image, audio and video to create unified models. This approach develops shared representations and learns correlations between modalities, enabling…

Computer Vision and Pattern Recognition · Computer Science 2024-09-19 Bilal Faye , Hanane Azzag , Mustapha Lebbah

Video Large Language Models (VLLMs) demonstrate strong video understanding but suffer from inefficiency due to redundant visual tokens. Existing pruning primary targets intra-frame spatial redundancy or prunes inside the LLM with…

Computer Vision and Pattern Recognition · Computer Science 2026-04-13 Jinlong Li , Liyuan Jiang , Haonan Zhang , Nicu Sebe

The advent of Large Multimodal Models (LMMs) has significantly enhanced Large Language Models (LLMs) to process and interpret diverse data modalities (e.g., image and video). However, as input complexity increases, particularly with long…

Computer Vision and Pattern Recognition · Computer Science 2025-12-23 Shilin Yan , Jiaming Han , Joey Tsai , Hongwei Xue , Rongyao Fang , Lingyi Hong , Ziyu Guo , Ray Zhang

Autoregressive (AR) models, long dominant in language generation, are increasingly applied to image synthesis but are often considered less competitive than Diffusion-based models. A primary limitation is the substantial number of image…

Audio-Visual Speech Recognition (AVSR) achieves robust speech recognition in noisy environments by combining auditory and visual information. However, recent Large Language Model (LLM) based AVSR systems incur high computational costs due…

Computer Vision and Pattern Recognition · Computer Science 2025-06-06 Jeong Hun Yeo , Hyeongseop Rha , Se Jin Park , Yong Man Ro

Large Speech Language Models (LSLMs) typically operate at high token rates (tokens/s) to ensure acoustic fidelity, yet this results in sequence lengths that far exceed the underlying semantic content, incurring prohibitive inference costs.…

Computation and Language · Computer Science 2026-04-09 Bajian Xiang , Tingwei Guo , Xuan Chen , Yang Han

Recent advancements in multimodal large language models (MLLMs) have demonstrated remarkable capabilities in processing diverse data types, yet significant disparities persist between human cognitive processes and computational approaches…

Computation and Language · Computer Science 2025-05-09 Dongxing Yu

Multimodal Large Language Models (MLLMs) have achieved impressive progress in vision-language alignment, yet they remain limited in visual-spatial reasoning. We first identify that this limitation arises from the attention mechanism: visual…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Zhaozhi Wang , Tong Zhang , Mingyue Guo , Yaowei Wang , Qixiang Ye

Conventional Vision-Language Models(VLMs) typically utilize a fixed number of vision tokens, regardless of task complexity. This one-size-fits-all strategy introduces notable inefficiencies: using excessive tokens leads to unnecessary…

Computer Vision and Pattern Recognition · Computer Science 2025-04-07 Junshan Hu , Jialiang Mao , Zhikang Liu , Zhongpu Xia , Peng Jia , Xianpeng Lang

Omni-modal large language models (om-LLMs) achieve unified audio-visual understanding by encoding video and audio into temporally aligned token sequences interleaved at the window level. However, processing these dense non-textual tokens…

Computer Vision and Pattern Recognition · Computer Science 2026-05-20 Zijie Xin , Jie Yang , Ruixiang Zhao , Tianyi Wang , Fengyun Rao , Jing Lyu , Xirong Li

Omnimodal Large Language Models (Omni-LLMs) incur substantial computational overhead due to the large number of multimodal input tokens they process, making token reduction essential for real-world deployment. Existing Omni-LLM pruning…

Computer Vision and Pattern Recognition · Computer Science 2026-05-13 Chaeyoung Jung , Kyeongha Rho , Joon Son Chung

Long video understanding remains challenging for Multi-modal Large Language Models (MLLMs) due to high memory costs and context-length limits. Prior approaches mitigate this by scoring and selecting frames/tokens within short clips, but…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Haozhe Qi , Kevin Qu , Mahdi Rad , Rui Wang , Alexander Mathis , Marc Pollefeys

Vision-Language Models (VLMs) process thousands of visual tokens per image alongside comparatively few text tokens, yet existing compression methods treat both modalities uniformly. We observe that the two modalities have fundamentally…

Machine Learning · Computer Science 2026-05-29 Yilin Feng , Ahmed Burak Gulhan , Mahmut Taylan Kandemir

Large Vision-Language Models (VLMs) have been extended to understand both images and videos. Visual token compression is leveraged to reduce the considerable token length of visual inputs. To meet the needs of different tasks, existing…

Computer Vision and Pattern Recognition · Computer Science 2024-12-13 Chenyu Yang , Xuan Dong , Xizhou Zhu , Weijie Su , Jiahao Wang , Hao Tian , Zhe Chen , Wenhai Wang , Lewei Lu , Jifeng Dai

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 Large Language models (LLMs) have demonstrated supreme capabilities in text understanding and generation, but cannot be directly applied to cross-modal tasks without fine-tuning. This paper proposes a cross-modal in-context learning…

Sound · Computer Science 2024-06-17 Dongchao Yang , Haohan Guo , Yuanyuan Wang , Rongjie Huang , Xiang Li , Xu Tan , Xixin Wu , Helen Meng

Recent studies in long video understanding have harnessed the advanced visual-language reasoning capabilities of Large Multimodal Models (LMMs), driving the evolution of video-LMMs specialized for processing extended video sequences.…

Computer Vision and Pattern Recognition · Computer Science 2026-03-06 Janghoon Cho , Jungsoo Lee , Munawar Hayat , Kyuwoong Hwang , Fatih Porikli , Sungha Choi