English
Related papers

Related papers: StreamingTOM: Streaming Token Compression for Effi…

200 papers

Multimodal large language models (MLLMs) have shown strong performance on offline video understanding, but most are limited to offline inference or have weak online reasoning, making multi-turn interaction over continuously arriving video…

Computer Vision and Pattern Recognition · Computer Science 2026-03-13 Lu Wang , Zhuoran Jin , Yupu Hao , Yubo Chen , Kang Liu , Yulong Ao , Jun Zhao

Modern multimodal large language models (MLLMs) can reason over hour-long video, yet their key-value (KV) cache grows linearly with time-quickly exceeding the fixed memory of phones, AR glasses, and edge robots. Prior compression schemes…

Image and Video Processing · Electrical Eng. & Systems 2025-10-27 Minsoo Kim , Kyuhong Shim , Jungwook Choi , Simyung Chang

Vision-Language Models (VLMs) have demonstrated strong performance on tasks such as video captioning and visual question answering. However, their growing scale and video-level inputs lead to significant computational and memory overhead,…

Hardware Architecture · Computer Science 2025-12-17 Chiyue Wei , Cong Guo , Junyao Zhang , Haoxuan Shan , Yifan Xu , Ziyue Zhang , Yudong Liu , Qinsi Wang , Changchun Zhou , Hai "Helen" Li , Yiran Chen

Real-time LLM interactions demand streamed token generations, where text tokens are progressively generated and delivered to users while balancing two objectives: responsiveness (i.e., low time-to-first-token) and steady generation…

Machine Learning · Computer Science 2025-10-06 Junyi Chen , Chuheng Du , Renyuan Liu , Shuochao Yao , Dingtian Yan , Jiang Liao , Shengzhong Liu , Fan Wu , Guihai Chen

Video Large Language Models (Video LLMs) achieve strong performance on video understanding tasks but suffer from high inference costs due to the large number of visual tokens. We propose KiToke, a training-free, query-agnostic token…

Computer Vision and Pattern Recognition · Computer Science 2026-04-07 Haifeng Huang , Yang Li

Context retrieval systems for LLM inference face a critical challenge: high retrieval latency creates a fundamental tension between waiting for complete context (poor time-to-first-token) and proceeding without it (reduced quality).…

Databases · Computer Science 2026-05-19 Rajveer Bachkaniwala , Chengqi Luo , Richard So , Divya Mahajan , Kexin Rong

Recent advances in Multimodal Large Language Models have greatly improved visual understanding and reasoning, yet their quadratic attention and offline training protocols make them ill-suited for streaming settings where frames arrive…

Computer Vision and Pattern Recognition · Computer Science 2026-02-26 Yulin Zhang , Cheng Shi , Sibei Yang

Recent developments in Video Large Language Models (Video LLMs) have enabled models to process hour-long videos and exhibit exceptional performance. Nonetheless, the Key-Value (KV) cache expands linearly over time, leading to substantial…

Computer Vision and Pattern Recognition · Computer Science 2026-04-24 Zhenyu Ning , Guangda Liu , Qihao Jin , Chengwei Li , Wenchao Ding , Minyi Guo , Jieru Zhao

This paper presents FluxMem, a training-free framework for efficient streaming video understanding. FluxMem adaptively compresses redundant visual memory through a hierarchical, two-stage design: (1) a Temporal Adjacency Selection (TAS)…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Yiweng Xie , Bo He , Junke Wang , Xiangyu Zheng , Ziyi Ye , Zuxuan Wu

Real-time understanding of continuous video streams is essential for interactive assistants and multimodal agents operating in dynamic environments. However, most existing video reasoning approaches follow a batch paradigm that defers…

Computer Vision and Pattern Recognition · Computer Science 2026-03-16 Zikang Liu , Longteng Guo , Handong Li , Ru Zhen , Xingjian He , Ruyi Ji , Xiaoming Ren , Yanhao Zhang , Haonan Lu , Jing Liu

Generative conversational interfaces powered by large language models (LLMs) typically stream output token-by-token at a rate determined by computational budget, often neglecting actual human reading speeds and the cognitive load associated…

Human-Computer Interaction · Computer Science 2025-07-25 Chang Xiao , Brenda Yang

Video Foundation Models (VFMs) exhibit remarkable visual generation performance, but struggle in compositional scenarios (e.g., motion, numeracy, and spatial relation). In this work, we introduce Test-Time Optimization and Memorization…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Leigang Qu , Ziyang Wang , Na Zheng , Wenjie Wang , Liqiang Nie , Tat-Seng Chua

Video large language models (VideoLLM) excel at video understanding, but face efficiency challenges due to the quadratic complexity of abundant visual tokens. Our systematic analysis of token compression methods for VideoLLMs reveals two…

Computer Vision and Pattern Recognition · Computer Science 2025-11-19 Xuyang Liu , Yiyu Wang , Junpeng Ma , Linfeng Zhang

Adapting Multimodal Large Language Models (MLLMs) for hour-long videos is bottlenecked by context limits. Dense visual streams saturate token budgets and exacerbate the lost-in-the-middle phenomenon. Existing heuristics, like sparse…

While streaming omni-video understanding demands continuous perception and proactive, real-time interaction, this crucial area remains largely under-explored. Current omni-modal methods are inherently designed for offline settings, limiting…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Ming Xie , Zizheng Huang , Xudong Tan , Chao Wang , Xiangyu Zeng , Wenxiao Wu , Tao Chen , Limin Wang , Yanwei Fu

Online Video Large Language Models (VideoLLMs) play a critical role in supporting responsive, real-time interaction. Existing methods focus on streaming perception, lacking a synchronized logical reasoning stream. However, directly applying…

Computer Vision and Pattern Recognition · Computer Science 2026-03-13 Yiran Guan , Liang Yin , Dingkang Liang , Jianzhong Ju , Zhenbo Luo , Jian Luan , Yuliang Liu , Xiang Bai

Recent Large Language Models have been enhanced with vision capabilities, enabling them to comprehend images, videos, and interleaved vision-language content. However, the learning methods of these large multimodal models typically treat…

Computer Vision and Pattern Recognition · Computer Science 2024-06-18 Joya Chen , Zhaoyang Lv , Shiwei Wu , Kevin Qinghong Lin , Chenan Song , Difei Gao , Jia-Wei Liu , Ziteng Gao , Dongxing Mao , Mike Zheng Shou

Balancing temporal resolution and spatial detail under limited compute budget remains a key challenge for video-based multi-modal large language models (MLLMs). Existing methods typically compress video representations using predefined…

Computer Vision and Pattern Recognition · Computer Science 2025-04-03 Min Shi , Shihao Wang , Chieh-Yun Chen , Jitesh Jain , Kai Wang , Junjun Xiong , Guilin Liu , Zhiding Yu , Humphrey Shi

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

Video Large Language Models (Video-LLMs) have demonstrated significant potential in the areas of video captioning, search, and summarization. However, current Video-LLMs still face challenges with long real-world videos. Recent methods have…

Computer Vision and Pattern Recognition · Computer Science 2025-11-11 Yilong Chen , Xiang Bai , Zhibin Wang , Chengyu Bai , Yuhan Dai , Ming Lu , Shanghang Zhang