中文
相关论文

相关论文: DynaTok: Temporally Adaptive and Positional Bias-A…

200 篇论文

Typical video modeling methods, such as LLava, represent videos as sequences of visual tokens, which are then processed by the LLM backbone for effective video understanding. However, this approach leads to a massive number of visual…

计算与语言 · 计算机科学 2025-06-05 Hongzhi Zhang , Jingyuan Zhang , Xingguang Ji , Qi Wang , Fuzheng Zhang

Recent advances in Video Large Language Models (VLLMs) have achieved remarkable video understanding capabilities, yet face critical efficiency bottlenecks due to quadratic computational growth with lengthy visual token sequences of long…

计算机视觉与模式识别 · 计算机科学 2025-12-09 Yulin Li , Haokun Gui , Ziyang Fan , Junjie Wang , Bin Kang , Bin Chen , Zhuotao Tian

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…

计算机视觉与模式识别 · 计算机科学 2025-03-31 Keda Tao , Can Qin , Haoxuan You , Yang Sui , Huan Wang

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…

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…

计算机视觉与模式识别 · 计算机科学 2026-04-07 Haifeng Huang , Yang Li

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…

计算机视觉与模式识别 · 计算机科学 2026-03-24 Junhao Du , Jialong Xue , Anqi Li , Jincheng Dai , Guo Lu

Accurate and efficient discrete video tokenization is essential for long video sequences processing. Yet, the inherent complexity and variable information density of videos present a significant bottleneck for current tokenizers, which…

计算机视觉与模式识别 · 计算机科学 2026-03-24 Haotian Ye , Qiyuan He , Jiaqi Han , Puheng Li , Jiaojiao Fan , Zekun Hao , Fitsum Reda , Yogesh Balaji , Huayu Chen , Sheng Liu , Angela Yao , James Zou , Stefano Ermon , Haoxiang Wang , Ming-Yu Liu

Recent advances in Video Large Language Models (VLLMs) have significantly enhanced their ability to understand video content. Nonetheless, processing long videos remains challenging due to high computational demands and the redundancy…

计算机视觉与模式识别 · 计算机科学 2025-09-30 Mengyue Wang , Shuo Chen , Kristian Kersting , Volker Tresp , Yunpu Ma

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.…

计算机视觉与模式识别 · 计算机科学 2026-03-06 Janghoon Cho , Jungsoo Lee , Munawar Hayat , Kyuwoong Hwang , Fatih Porikli , Sungha Choi

In this paper, we present LLaVA-Scissor, a training-free token compression strategy designed for video multimodal large language models. Previous methods mostly attempt to compress tokens based on attention scores, but fail to effectively…

计算机视觉与模式识别 · 计算机科学 2025-06-30 Boyuan Sun , Jiaxing Zhao , Xihan Wei , Qibin Hou

As Video Large Language Models (Video-LLMs) scale to longer and more complex videos, their inference cost grows rapidly due to the large volume of visual tokens accumulated across frames. Training-free token compression has emerged as a…

计算机视觉与模式识别 · 计算机科学 2026-05-13 Minseok Kang , Minhyeok Lee , Jungho Lee , Minjung Kim , Donghyeong Kim , Dayeon Lee , Heeseung Choi , Ig-jae Kim , Sangyoun Lee

Efficient video tokenization remains a key bottleneck in learning general purpose vision models that are capable of processing long video sequences. Prevailing approaches are restricted to encoding videos to a fixed number of tokens, where…

机器学习 · 计算机科学 2025-02-04 Wilson Yan , Volodymyr Mnih , Aleksandra Faust , Matei Zaharia , Pieter Abbeel , Hao Liu

Recent advances in Large Language Models (LLMs) have led to significant breakthroughs in video understanding. However, existing models still struggle with long video processing due to the context length constraint of LLMs and the vast…

计算机视觉与模式识别 · 计算机科学 2025-04-15 Haoran Hao , Jiaming Han , Yiyuan Zhang , Xiangyu Yue

We propose AdapTok, an adaptive temporal causal video tokenizer that can flexibly allocate tokens for different frames based on video content. AdapTok is equipped with a block-wise masking strategy that randomly drops tail tokens of each…

计算机视觉与模式识别 · 计算机科学 2025-10-15 Yan Li , Changyao Tian , Renqiu Xia , Ning Liao , Weiwei Guo , Junchi Yan , Hongsheng Li , Jifeng Dai , Hao Li , Xue Yang

Training-free video large language models (LLMs) leverage pretrained Image LLMs to process video content without the need for further training. A key challenge in such approaches is the difficulty of retaining essential visual and temporal…

计算机视觉与模式识别 · 计算机科学 2025-03-17 Leqi Shen , Tao He , Guoqiang Gong , Fan Yang , Yifeng Zhang , Pengzhang Liu , Sicheng Zhao , Guiguang Ding

Unlike offline processing, streaming video vision-language models face two fundamental constraints: causality and accumulation. Causality prevents access to future frames that offline methods exploit, while accumulation causes tokens to…

计算机视觉与模式识别 · 计算机科学 2026-03-17 Xueyi Chen , Keda Tao , Kele Shao , Huan Wang

Video Large Language Models (VideoLLMs) have made significant strides in video understanding but struggle with long videos due to the limitations of their backbone LLMs. Existing solutions rely on length extrapolation, which is…

计算机视觉与模式识别 · 计算机科学 2025-03-25 Xiao Wang , Qingyi Si , Jianlong Wu , Shiyu Zhu , Li Cao , Liqiang Nie

Video large language models (Video-LLMs) have demonstrated strong capabilities in video understanding tasks. However, their practical deployment is still hindered by the inefficiency introduced by processing massive amounts of visual…

计算机视觉与模式识别 · 计算机科学 2026-05-29 Hesong Wang , Xin Jin , Lu Lu , Chenhaowen Li , Jian Chen , Qiang Liu , Huan Wang

Token-based video representation has emerged as a promising approach for enabling large language models (LLMs) to interpret video content. However, existing token reduction techniques, such as pruning and merging, often disrupt essential…

计算机视觉与模式识别 · 计算机科学 2025-09-30 Haichao Zhang , Yun Fu

Large Vision-Language Models (LVLMs) excel in visual understanding and reasoning, but the excessive visual tokens lead to high inference costs. Although recent token reduction methods mitigate this issue, they mainly target single-turn…

计算机视觉与模式识别 · 计算机科学 2026-03-24 Yi Wang , Haofei Zhang , Qihan Huang , Anda Cao , Gongfan Fang , Wei Wang , Xuan Jin , Jie Song , Mingli Song , Xinchao Wang
‹ 上一页 1 2 3 10 下一页 ›