English
Related papers

Related papers: XStreamVGGT: Extremely Memory-Efficient Streaming …

200 papers

Streaming video large language models (LLMs) are increasingly used for real-time multimodal tasks such as video captioning, question answering, conversational agents, and augmented reality. However, these models face fundamental memory and…

Image and Video Processing · Electrical Eng. & Systems 2025-12-25 Donghyuk Kim , Sejeong Yang , Wonjin Shin , Joo-Young Kim

Video diffusion models (DMs) have enabled high-quality video synthesis. Yet, their substantial computational and memory demands pose serious challenges to real-world deployment, even on high-end GPUs. As a commonly adopted solution,…

Computer Vision and Pattern Recognition · Computer Science 2026-01-29 Yushi Huang , Ruihao Gong , Jing Liu , Yifu Ding , Chengtao Lv , Haotong Qin , Jun Zhang

Vision-language models (VLMs) could power real-time assistants and autonomous agents, but they face a critical challenge: understanding near-infinite video streams without escalating latency and memory usage. Processing entire videos with…

Computer Vision and Pattern Recognition · Computer Science 2025-10-13 Ruyi Xu , Guangxuan Xiao , Yukang Chen , Liuning He , Kelly Peng , Yao Lu , Song Han

Streaming video question answering (Streaming Video QA) poses distinct challenges for multimodal large language models (MLLMs), as video frames arrive sequentially and user queries can be issued at arbitrary time points. Existing solutions…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Haocheng Lu , Nan Zhang , Wei Tao , Xiaoyang Qu , Guokuan Li , Jiguang Wan , Jianzong Wang

We present Reversible Vision Transformers, a memory efficient architecture design for visual recognition. By decoupling the GPU memory requirement from the depth of the model, Reversible Vision Transformers enable scaling up architectures…

Computer Vision and Pattern Recognition · Computer Science 2023-02-10 Karttikeya Mangalam , Haoqi Fan , Yanghao Li , Chao-Yuan Wu , Bo Xiong , Christoph Feichtenhofer , Jitendra Malik

3D instance segmentation methods typically rely on high-quality point clouds or posed RGB-D scans, requiring complex multi-stage processing pipelines, and are highly sensitive to reconstruction noise. While recent feed-forward transformers…

Computer Vision and Pattern Recognition · Computer Science 2026-03-23 Jinyuan Qu , Hongyang Li , Lei Zhang

3D Gaussian Splatting (3DGS) has emerged as a high-fidelity and efficient paradigm for online free-viewpoint video (FVV) reconstruction, offering viewers rapid responsiveness and immersive experiences. However, existing online methods face…

Computer Vision and Pattern Recognition · Computer Science 2025-11-17 Jiacong Chen , Qingyu Mao , Youneng Bao , Xiandong Meng , Fanyang Meng , Ronggang Wang , Yongsheng Liang

Vision-Language-Action (VLA) models offer a unified framework for robotic perception and control, but their ability to scale to real-world, long-horizon tasks is limited by the high computational cost of attention and the large memory…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Wanshun Xu , Long Zhuang , Lianlei Shan

Long streaming video QA remains challenging due to growing visual tokens and limited reasoning length of large language models (LLMs). KV-caching stores the Key-Value (KV) of the historical tokens via LLM prefill and enables more efficient…

Computer Vision and Pattern Recognition · Computer Science 2026-05-22 Junbin Xiao , Jiajun Chen , Tianxiang Sun , Xun Yang , Angela Yao

Huge memory consumption has been a major bottleneck for deploying high-throughput large language models in real-world applications. In addition to the large number of parameters, the key-value (KV) cache for the attention mechanism in the…

Computation and Language · Computer Science 2024-06-05 Haoyi Wu , Kewei Tu

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…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Xueyi Chen , Keda Tao , Kele Shao , Huan Wang

Online free-viewpoint video (FVV) streaming is a challenging problem, which is relatively under-explored. It requires incremental on-the-fly updates to a volumetric representation, fast training and rendering to satisfy real-time…

Computer Vision and Pattern Recognition · Computer Science 2024-12-06 Sharath Girish , Tianye Li , Amrita Mazumdar , Abhinav Shrivastava , David Luebke , Shalini De Mello

Video tokenization procedure is critical for a wide range of video processing tasks. Most existing approaches directly transform video into fixed-grid and patch-wise tokens, which exhibit limited versatility. Spatially, uniformly allocating…

Computer Vision and Pattern Recognition · Computer Science 2025-08-18 Zhenghao Chen , Zicong Chen , Lei Liu , Yiming Wu , Dong Xu

Online free-viewpoint video (FVV) reconstruction is challenged by slow per-frame optimization, inconsistent motion estimation, and unsustainable storage demands. To address these challenges, we propose the Reconfigurable Continuum Gaussian…

Image and Video Processing · Electrical Eng. & Systems 2025-10-31 Jiaye Fu , Qiankun Gao , Chengxiang Wen , Yanmin Wu , Siwei Ma , Jiaqi Zhang , Jian Zhang

In this study, we introduce adaptive KV cache compression, a plug-and-play method that reduces the memory footprint of generative inference for Large Language Models (LLMs). Different from the conventional KV cache that retains key and…

Computation and Language · Computer Science 2024-10-31 Suyu Ge , Yunan Zhang , Liyuan Liu , Minjia Zhang , Jiawei Han , Jianfeng Gao

The video grounding (VG) task aims to locate the queried action or event in an untrimmed video based on rich linguistic descriptions. Existing proposal-free methods are trapped in complex interaction between video and query, overemphasizing…

Computer Vision and Pattern Recognition · Computer Science 2023-08-14 Kun Li , Dan Guo , Meng Wang

The development of large language models (LLMs) has significantly expanded model sizes, resulting in substantial GPU memory requirements during inference. The key and value storage of the attention map in the KV (key-value) cache accounts…

Machine Learning · Computer Science 2024-10-25 Yifei Yang , Zouying Cao , Qiguang Chen , Libo Qin , Dongjie Yang , Hai Zhao , Zhi Chen

Vision agent memory has shown remarkable effectiveness in streaming video understanding. However, storing such memory for videos incurs substantial memory overhead, leading to high costs in both storage and computation. To address this…

Computer Vision and Pattern Recognition · Computer Science 2026-04-24 Junxi Wang , Te Sun , Jiayi Zhu , Junxian Li , Haowen Xu , Zichen Wen , Xuming Hu , Zhiyu Li , Linfeng Zhang

Streaming video understanding with large vision-language models (VLMs) requires a compact memory that can support future reasoning over an ever-growing visual history. A common solution is to compress the key-value (KV) cache, but existing…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Ailar Mahdizadeh , Puria Azadi , Muchen Li , Xiangteng He , Leonid Sigal

Recent feed-forward reconstruction models, such as VGGT, have proven competitive with traditional optimization-based reconstructors while also providing geometry-aware features useful for other tasks. Here, we show that the quality of these…